© 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. 184027
    Prev
    Next
    INDEX
    Explanations

    things get, contributed to, owed

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

    something specific

    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
     %).
    0.50
     trimester
    0.47
     scary
    0.46
     %)
    0.45
     ఎక్కువ
    0.43
     dielectric
    0.43
     эффективность
    0.41
     %),
    0.41
     hòa
    0.40
     मुंह
    0.40
    POSITIVE LOGITS
    through
    0.56
    𝐡
    0.55
    that
    0.54
    writ
    0.53
    models
    0.53
    accumulation
    0.53
    locally
    0.53
    others
    0.52
    gig
    0.52
    quickly
    0.52
    Activations Density 0.000%

    No Known Activations