© 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. 208874
    Prev
    Next
    INDEX
    Explanations

    emails and newsletters

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

    lists or code segments

    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
    蛏
    0.59
    黾
    0.50
     zusätzlichen
    0.49
    独立的
    0.49
    髡
    0.47
     zusätzliche
    0.46
    ளுடன்
    0.45
    Combin
    0.45
    чко
    0.44
    다
    0.44
    POSITIVE LOGITS
     WE
    0.46
     MO
    0.45
     Indica
    0.45
    reven
    0.45
     МО
    0.45
     é
    0.44
     GAR
    0.44
     vans
    0.44
    bw
    0.43
     BE
    0.42
    Activations Density 0.001%

    No Known Activations