© 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. 234561
    Prev
    Next
    INDEX
    Explanations

    contact you

    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
     everywhere
    0.54
     überall
    0.52
    ！】
    0.47
     incremento
    0.45
     veloce
    0.45
     gerakan
    0.44
    ៕
    0.44
    χής
    0.43
     männ
    0.42
     γεν
    0.42
    POSITIVE LOGITS
    on
    0.62
    structor
    0.53
    아
    0.49
    with
    0.48
    ad
    0.47
    c
    0.46
    g
    0.46
    t
    0.45
    ia
    0.45
     Gud
    0.45
    Activations Density 0.001%

    No Known Activations