© 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. 31105
    Prev
    Next
    INDEX
    Explanations

    allocating tensor

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

    The neuron lights up on prominent technical content words (key nouns or verbs) in documentation or code comments.

    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
     Automobil
    -0.77
     uniquely
    -0.76
     vegetable
    -0.76
    UIImage
    -0.75
     inspirational
    -0.75
     Coordinating
    -0.72
    dillera
    -0.71
     още
    -0.71
     Pollut
    -0.70
    🌭
    -0.70
    POSITIVE LOGITS
     }}=
    0.81
    avance
    0.77
     requiere
    0.76
     dials
    0.75
     вчера
    0.75
    mari
    0.73
    ̣n
    0.73
     unloaded
    0.73
     Regime
    0.70
    Cent
    0.70
    Activations Density 0.008%

    No Known Activations