© 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. 141541
    Prev
    Next
    INDEX
    Explanations

    objects and cultural artifacts

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

    early recovery

    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
    >\
    0.52
    趔
    0.46
     पूर्वानु
    0.46
    しているので
    0.46
    ❎
    0.45
     областях
    0.45
     考え
    0.44
    \},\
    0.44
     অবস্থানে
    0.44
     বর্ণের
    0.43
    POSITIVE LOGITS
    اندار
    0.44
     auctions
    0.44
     museums
    0.43
    ه
    0.43
    ر
    0.43
    au
    0.42
     lavage
    0.42
     samh
    0.42
     housewives
    0.42
     consumers
    0.42
    Activations Density 0.000%

    No Known Activations