© 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. 135963
    Prev
    Next
    INDEX
    Explanations

    registration card

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

    ethics, risk, removals

    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
     kirj
    0.49
    는
    0.46
    ül
    0.45
     maß
    0.45
     bein
    0.44
     kuş
    0.43
     själv
    0.43
     begyn
    0.42
     férfi
    0.41
     tuz
    0.41
    POSITIVE LOGITS
    substantial
    0.48
    p
    0.48
    ί
    0.48
     onDelete
    0.45
    ля
    0.44
     интересно
    0.44
     снаб
    0.44
    на
    0.44
    ву
    0.43
    respective
    0.43
    Activations Density 0.001%

    No Known Activations