© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141431
    Prev
    Next
    INDEX
    Explanations

    departure packs

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

    counting numbers and sequential events

    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
    ।,
    0.45
     छि
    0.44
    ראל
    0.43
     hết
    0.42
    𝘸
    0.41
    ┙
    0.41
    ई
    0.40
    ,((
    0.40
    🥯
    0.39
    이지만
    0.39
    POSITIVE LOGITS
    hock
    0.48
    in
    0.48
    lungen
    0.46
     paket
    0.46
     USB
    0.45
    adapter
    0.43
     protector
    0.43
     gadgets
    0.42
    lungs
    0.42
     Jahres
    0.42
    Activations Density 0.002%

    No Known Activations