© 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. 74246
    Prev
    Next
    INDEX
    Explanations

    inspired by, band an audience, coupon led, where few

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

    separators like :**

    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
     lockers
    0.59
     eos
    0.52
    eiros
    0.52
     sparsim
    0.52
     receptors
    0.51
     transistors
    0.51
    ♿
    0.51
     merciful
    0.50
    レール
    0.50
     junctions
    0.50
    POSITIVE LOGITS
    权
    0.48
    杜
    0.46
    CLionProjects
    0.45
    ID
    0.44
    ü
    0.44
    IM
    0.44
    翦
    0.43
    STATEMENT
    0.42
    祺
    0.42
     Dil
    0.42
    Activations Density 0.000%

    No Known Activations