© 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. 104982
    Prev
    Next
    INDEX
    Explanations

    list suffixes

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

    unit, channel, static, adapt

    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
    ="'$(
    0.46
    قاء
    0.44
    ح
    0.43
     Entity
    0.42
     گرفتن
    0.42
    ಟ
    0.42
    }={\
    0.41
    ENTITY
    0.41
    >+</
    0.40
    >((
    0.40
    POSITIVE LOGITS
     convolutions
    0.52
     comparisons
    0.51
     manifestations
    0.51
     outras
    0.49
     salons
    0.49
     boomers
    0.49
     connotations
    0.46
     inspirations
    0.46
    autres
    0.46
     longa
    0.46
    Activations Density 0.001%

    No Known Activations