© 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. 150928
    Prev
    Next
    INDEX
    Explanations

    select tickets

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

    risk and reward trade-offs

    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
    땠
    0.45
    |^
    0.45
     facilidad
    0.43
    |=
    0.43
    बूझ
    0.42
    続く
    0.42
     sturdy
    0.42
     независи
    0.42
    フィール
    0.41
     başvur
    0.41
    POSITIVE LOGITS
    р
    0.62
    ر
    0.56
    ک
    0.55
    रा
    0.54
    س
    0.51
    র
    0.50
    ſelf
    0.49
    سری
    0.49
    iece
    0.48
    ichni
    0.48
    Activations Density 0.000%

    No Known Activations