© 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. 88934
    Prev
    Next
    INDEX
    Explanations

    mail from

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

    configure sentry-cli

    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
    瞅
    0.47
    嶈
    0.45
    য়
    0.45
     tailed
    0.44
    坍
    0.44
     whanne
    0.43
     hooded
    0.43
    嵃
    0.42
    指针
    0.42
    婹
    0.42
    POSITIVE LOGITS
    iel
    0.46
    Amp
    0.46
    one
    0.46
    peria
    0.46
    chant
    0.46
    dot
    0.45
    Recipient
    0.45
    amic
    0.45
    ookie
    0.45
    met
    0.45
    Activations Density 0.002%

    No Known Activations