© 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. 26907
    Prev
    Next
    INDEX
    Explanations

    three types

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

    not followed by verb or past tense verbs

    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
    p
    0.53
    Prov
    0.50
     увагу
    0.49
    o
    0.49
    sig
    0.49
    BMI
    0.48
    non
    0.48
    e
    0.47
    g
    0.47
    fatt
    0.46
    POSITIVE LOGITS
     mús
    0.50
     ás
    0.49
     difíc
    0.48
     postgres
    0.48
    ๎
    0.48
     स्मृति
    0.46
     mound
    0.45
    وات
    0.44
     trilogy
    0.44
    át
    0.44
    Activations Density 0.000%

    No Known Activations