© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    application and implementation details

    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
    x
    0.52
     CaCl
    0.48
     aliqu
    0.46
     Sequences
    0.45
    A
    0.45
     clones
    0.45
     $)$
    0.45
     e
    0.44
    iót
    0.44
     faç
    0.44
    POSITIVE LOGITS
    agangan
    0.53
    atters
    0.52
     menerapkan
    0.52
     diterapkan
    0.51
    гаа
    0.50
     گے۔
    0.49
    ል።
    0.48
    abhut
    0.48
    ocument
    0.48
     آہ
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.