© 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. 58867
    Prev
    Next
    INDEX
    Explanations

    string, tied, straps

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

    string pulling you

    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
     SCHEDULE
    0.48
     GUARD
    0.45
     Gré
    0.45
     ATT
    0.43
     LIABILITY
    0.43
     ولي
    0.43
     WHEN
    0.41
    缠
    0.41
     MOST
    0.41
     THE
    0.41
    POSITIVE LOGITS
    こちら
    0.49
    संपादन
    0.44
     rainforest
    0.43
    ভারত
    0.42
    ◔
    0.41
     thumb
    0.41
    用水
    0.41
     as
    0.40
     وغيرها
    0.40
    ଐ
    0.40
    Activations Density 0.000%

    No Known Activations