© 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. 245650
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

    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
    January
    0.46
    Pourquoi
    0.46
    %"
    0.45
    анали
    0.45
     mouve
    0.44
    ヵ
    0.44
    <unused0>
    0.44
    ❇
    0.44
    ร่
    0.43
    Gestion
    0.43
    POSITIVE LOGITS
     TV
    0.53
     Dome
    0.51
     Epi
    0.50
     LPA
    0.49
    ive
    0.49
     Episcopal
    0.49
     Subscription
    0.49
     EPC
    0.49
     Lyapunov
    0.48
    thers
    0.48
    Activations Density 0.000%

    No Known Activations