© 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. 37616
    Prev
    Next
    INDEX
    Explanations

    digits followed by specific words or punctuation

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

    collapsing multiple universes

    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
     interestingly
    0.49
     bituminous
    0.44
    <unused73>
    0.42
     trivalent
    0.42
     evanescent
    0.41
    <unused16>
    0.41
     menghasilkan
    0.41
     arterioles
    0.41
    льної
    0.41
     fluidized
    0.40
    POSITIVE LOGITS
    UpdateTime
    0.47
    '
    0.44
    ম
    0.44
    জ
    0.44
    жи
    0.43
    responseTime
    0.42
    প
    0.42
    hej
    0.41
    进度
    0.41
     Temps
    0.41
    Activations Density 0.000%

    No Known Activations