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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71229
    Prev
    Next
    INDEX
    Explanations

    from which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     как
    -1.80
    用的
    -1.61
    5
    -1.59
     merusak
    -1.55
    」。
    -1.51
    一样的
    -1.46
    6
    -1.46
     на
    -1.46
    自分は
    -1.46
     باسلام
    -1.45
    POSITIVE LOGITS
    ,
    2.27
     to
    2.13
    ፨
    1.69
    tedrale
    1.63
    nă
    1.59
     pozdě
    1.59
    estimates
    1.57
     Saltar
    1.56
     Lengkap
    1.55
    providedIn
    1.53
    Activations Density 0.024%

    No Known Activations