© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17846
    Prev
    Next
    INDEX
    Explanations

    plan, location, pain

    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
     Utilisez
    0.44
     NaOH
    0.43
    教材
    0.42
     setText
    0.42
     পুস্তকের
    0.42
    𝐚
    0.42
     utilizan
    0.42
     и
    0.41
     અને
    0.41
     THIS
    0.40
    POSITIVE LOGITS
    zam
    0.45
     الات
    0.44
    por
    0.44
     מל
    0.42
     Stern
    0.42
    damn
    0.42
    different
    0.40
     repressive
    0.40
     škola
    0.40
    ynet
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.