© 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. 34-GEMMASCOPE-RES-131K
    7. 81702
    Prev
    Next
    INDEX
    Explanations

    rated PG, R, X ratings

    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_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
    イッチ
    -0.73
     VMs
    -0.73
    kok
    -0.72
    上学
    -0.71
    こだ
    -0.69
    braith
    -0.68
    maris
    -0.68
    胡
    -0.67
     Khat
    -0.67
     Kari
    -0.65
    POSITIVE LOGITS
     PG
    3.22
    PG
    2.56
     pg
    2.23
     Rated
    2.22
     rated
    2.09
    pg
    2.03
    Rated
    1.97
     R
    1.89
    rated
    1.76
     Pg
    1.59
    Activations Density 0.023%

    No Known Activations