© 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. 36905
    Prev
    Next
    INDEX
    Explanations

    harm animals

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

    recipe for, aiming for, Let's analyze

    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
    jaro
    0.49
     selben
    0.45
     ט
    0.44
    Бар
    0.44
     sver
    0.44
    T
    0.44
     knack
    0.44
    Se
    0.43
    Einzel
    0.42
     f
    0.42
    POSITIVE LOGITS
    簑
    0.48
    මට
    0.48
    ILLE
    0.45
     INVESTMENT
    0.45
     আইনশৃঙ্খলা
    0.45
    icione
    0.44
    ませんので
    0.44
    权的
    0.44
    হরণ
    0.43
    ieniu
    0.43
    Activations Density 0.000%

    No Known Activations