© 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. 160002
    Prev
    Next
    INDEX
    Explanations

    teams, male, Steve, stop, form, little

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

    gaming, code, technology, biology

    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
     itinéraires
    0.54
    𝙥
    0.53
    ርዝ
    0.52
    欬
    0.51
    媝
    0.50
    ج
    0.50
     Egipto
    0.50
    昛
    0.50
    ولندا
    0.49
     باذن
    0.49
    POSITIVE LOGITS
    ase
    0.49
    '
    0.45
    ids
    0.45
    esa
    0.45
    oche
    0.44
    ic
    0.43
    ild
    0.42
     participated
    0.42
     vegetarians
    0.42
    ased
    0.41
    Activations Density 0.001%

    No Known Activations