© 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. 2761
    Prev
    Next
    INDEX
    Explanations

    numbers and quantifying phrases

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

    detecting specific entities and properties

    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
    day
    0.68
    the
    0.67
    Y
    0.65
    s
    0.64
    of
    0.63
    E
    0.63
    two
    0.62
    J
    0.61
    us
    0.59
    e
    0.59
    POSITIVE LOGITS
     Congresso
    0.57
     reconnaît
    0.56
     Álvarez
    0.53
     errichtet
    0.53
     somit
    0.53
     നിൽ
    0.53
     vostre
    0.50
    édez
    0.50
     Autoren
    0.50
     Produkten
    0.50
    Activations Density 0.000%

    No Known Activations