© 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. 217186
    Prev
    Next
    INDEX
    Explanations

    parentheses and periods

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

    minefields, fear, lion, aspects

    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
    Area
    0.48
    MainActivity
    0.46
    Assembly
    0.45
    HEL
    0.45
    ARE
    0.44
    ::-
    0.44
    Watson
    0.44
    PP
    0.44
    STORAGE
    0.44
     సర్
    0.44
    POSITIVE LOGITS
    ्तर
    0.57
    グループ
    0.49
     dezvolt
    0.49
     développ
    0.49
    این
    0.48
    ా
    0.48
     squadre
    0.47
     takım
    0.47
    که
    0.47
     biologique
    0.47
    Activations Density 0.001%

    No Known Activations