© 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. 63905
    Prev
    Next
    INDEX
    Explanations

    programming code and configurations

    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
     pebbles
    0.44
     storylines
    0.43
    タウン
    0.43
     boulders
    0.42
     rojos
    0.41
    重複
    0.41
     बज
    0.41
    언
    0.41
     rivets
    0.40
    листы
    0.40
    POSITIVE LOGITS
     successor
    0.43
     GMP
    0.42
    दरम्यान
    0.41
     Banquet
    0.40
    蜕
    0.40
     Cluster
    0.39
     Spectral
    0.39
     মৃত্য
    0.38
     Intermediate
    0.38
     surg
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.