© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159306
    Prev
    Next
    INDEX
    Explanations

    monthly reports, minimum allowable

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

    Amnesty International legal reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remarkably
    0.46
     Remarkably
    0.44
    surprisingly
    0.43
     sages
    0.42
     अनुभवी
    0.42
     दिसून
    0.42
    層
    0.42
    隨
    0.42
     いたし
    0.41
     marquée
    0.41
    POSITIVE LOGITS
    শকা
    0.52
     mortgage
    0.49
    ীরের
    0.46
     кандай
    0.45
     prepayment
    0.45
    থাৎ
    0.45
     domande
    0.45
    োডে
    0.43
    ల్య
    0.43
     pembayaran
    0.43
    Activations Density 0.001%

    No Known Activations