© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47932
    Prev
    Next
    INDEX
    Explanations

    urgency, threats, or specific list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exclu
    0.48
     ön
    0.45
     lega
    0.44
    𝟰
    0.43
    日志
    0.43
     eel
    0.42
     söyle
    0.42
     unabhängig
    0.42
     தலைநக
    0.42
    audit
    0.42
    POSITIVE LOGITS
     ፣
    0.48
    ッテリー
    0.47
     temporarily
    0.46
     temporary
    0.44
    ดวก
    0.44
     grandeza
    0.44
    settes
    0.43
     stardom
    0.43
    當時
    0.42
     stimulus
    0.41
    Activations Density 0.002%

    No Known Activations