© 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. 236430
    Prev
    Next
    INDEX
    Explanations

    already committed

    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
     মুছে
    0.56
    𝙪
    0.53
     వ
    0.52
     مون
    0.50
     روم
    0.50
     colomb
    0.49
     మాత్రమే
    0.49
     কেনার
    0.48
     గో
    0.48
    哴
    0.48
    POSITIVE LOGITS
     органами
    0.51
     delegates
    0.49
    жат
    0.48
     lysed
    0.48
     overlapped
    0.47
     concentric
    0.46
    њу
    0.46
     laboratories
    0.46
    <0x80>
    0.45
     docked
    0.45
    Activations Density 0.000%

    No Known Activations