© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    right to future

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

    information systems upgrades

    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
    牷
    0.52
    硌
    0.50
    坌
    0.48
    щик
    0.47
    不容易
    0.47
    癃
    0.46
    בּ
    0.46
    λεσ
    0.45
    荸
    0.45
    搠
    0.45
    POSITIVE LOGITS
     доку
    0.45
    onia
    0.45
     diversos
    0.45
     renewals
    0.44
     vasos
    0.44
    tilde
    0.43
     clubes
    0.43
     reim
    0.43
     colaboradores
    0.42
     رحمه
    0.42
    Activations Density 0.000%

    No Known Activations