© 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. 77730
    Prev
    Next
    INDEX
    Explanations

    conference opponents

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

    The neuron fires on hardware‐oriented identifiers and file references (e.g. “File”, “system”, “STM32F4xx devices”).

    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
     roky
    -0.82
     tæn
    -0.78
     Chairman
    -0.77
    nader
    -0.77
     ткань
    -0.76
    },'
    -0.75
     tanken
    -0.75
     Presidente
    -0.75
     Ná
    -0.74
    𖥦
    -0.73
    POSITIVE LOGITS
     persons
    1.00
     Surname
    0.83
    ѓ
    0.81
     ABBRE
    0.76
    Вар
    0.75
     Bosco
    0.74
    Dibrom
    0.74
    𝕚
    0.71
    洛克
    0.71
     sre
    0.71
    Activations Density 0.026%

    No Known Activations