© 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. 47950
    Prev
    Next
    INDEX
    Explanations

    final result sections

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

    consequences and conditions

    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
    HR
    0.52
    )^*
    0.49
    COR
    0.48
    TR
    0.48
    UND
    0.48
     kev
    0.47
    Fri
    0.47
    ↵
    0.47
    CC
    0.46
    SS
    0.46
    POSITIVE LOGITS
     repercussions
    0.58
    㓶
    0.55
     utterances
    0.52
     ideologies
    0.49
     consecuencias
    0.49
    рії
    0.47
     создал
    0.47
    媑
    0.47
     உச்ச
    0.47
    㖷
    0.47
    Activations Density 0.000%

    No Known Activations