© 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. 194808
    Prev
    Next
    INDEX
    Explanations

    owned entirely

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

    weighting inputs for meaning

    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
     vindt
    0.46
     مك
    0.44
     Alberto
    0.43
     Jacksonville
    0.43
    燄
    0.43
     joj
    0.42
     تج
    0.42
     FIB
    0.41
     Jorge
    0.41
     Francisco
    0.41
    POSITIVE LOGITS
    Ⲏ
    0.58
    を取り
    0.50
    Surgery
    0.47
    нд
    0.47
    ersonal
    0.46
     échanges
    0.45
    🩷
    0.45
    ordial
    0.45
    Ordinate
    0.45
    公演
    0.45
    Activations Density 0.000%

    No Known Activations