© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3145
    Prev
    Next
    INDEX
    Explanations

    ambient or room temperature

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on technical method steps and their quantitative parameters—e.g. numeric values, units, and experimental‐condition markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skrift
    -0.74
    håll
    -0.74
     multiplayer
    -0.74
    叵
    -0.71
    égard
    -0.71
    DeclareMath
    -0.69
    ológico
    -0.68
     privatization
    -0.67
     WJ
    -0.67
     friendships
    -0.66
    POSITIVE LOGITS
     ambient
    4.06
    Ambient
    3.25
    ambient
    3.20
     Ambient
    3.17
     room
    2.91
     atmospheric
    2.84
     Atmospheric
    2.17
    room
    2.13
     Room
    2.09
    Atmospheric
    2.05
    Activations Density 0.147%

    No Known Activations