© 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. 227557
    Prev
    Next
    INDEX
    Explanations

    created name

    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
    adik
    0.53
    ü
    0.52
    كت
    0.50
    ünden
    0.47
    كة
    0.47
     akt
    0.46
     höher
    0.46
    ikte
    0.46
    idur
    0.45
    varande
    0.45
    POSITIVE LOGITS
     علی
    0.54
     strut
    0.49
    Յ
    0.49
    秀
    0.48
    the
    0.48
    少し
    0.48
    そして
    0.47
     taux
    0.47
    良かった
    0.46
     pourcentage
    0.46
    Activations Density 0.000%

    No Known Activations