© 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. 78246
    Prev
    Next
    INDEX
    Explanations

    quantifying positive outcomes

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

    harm, control, or conflict

    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
    in
    0.54
    ini
    0.49
    w
    0.46
    l
    0.46
    username
    0.45
     username
    0.45
     into
    0.44
     in
    0.43
     overseas
    0.43
     left
    0.43
    POSITIVE LOGITS
     растения
    0.54
    房屋
    0.53
     guérison
    0.52
    甾
    0.50
     salvare
    0.49
    ป้องกัน
    0.48
    恢复
    0.48
    ❣️
    0.48
    ปลอดภัย
    0.48
     مقاوم
    0.48
    Activations Density 0.000%

    No Known Activations