© 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. 208230
    Prev
    Next
    INDEX
    Explanations

    login/Login

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

    check the platforms

    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
     Mosca
    0.46
     spirito
    0.45
     contesto
    0.42
     \%$,
    0.42
     ambito
    0.42
     Cynthia
    0.41
    FIL
    0.41
     Io
    0.40
    重視
    0.40
     FAR
    0.40
    POSITIVE LOGITS
    anız
    0.51
     заменить
    0.51
    login
    0.50
    ir
    0.50
     жана
    0.48
    blanc
    0.48
    aná
    0.47
    л
    0.47
    ер
    0.47
     Login
    0.47
    Activations Density 0.000%

    No Known Activations