© 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. 116980
    Prev
    Next
    INDEX
    Explanations

    wide-angle lens used for photos

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

    Key Management

    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
    t
    0.54
    the
    0.51
    when
    0.49
    tes
    0.48
     estimations
    0.47
    time
    0.46
     différentes
    0.44
    tru
    0.44
     ellipsis
    0.44
    ticks
    0.44
    POSITIVE LOGITS
     issuer
    0.48
     புர
    0.46
    ᱸ
    0.45
    iamiento
    0.45
    istema
    0.44
    ंड
    0.43
    undant
    0.43
     કંપની
    0.43
     Disbursements
    0.43
     ску
    0.42
    Activations Density 0.001%

    No Known Activations