© 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. 9543
    Prev
    Next
    INDEX
    Explanations

    county addresses Douglas

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

    turn markers and conversation

    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
    IGATION
    0.43
     sows
    0.40
    यत्त
    0.38
    لوث
    0.37
     RADIOACTIVE
    0.37
     chemokine
    0.37
    Gravestone
    0.37
    䒾
    0.37
     filamentous
    0.36
    CUSSION
    0.36
    POSITIVE LOGITS
    (!
    0.43
    ity
    0.43
    ↵
    0.41
    or
    0.41
    tag
    0.41
    ;
    0.40
    å
    0.39
    ed
    0.39
     Ultra
    0.38
    &
    0.38
    Activations Density 0.053%

    No Known Activations