© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13187
    Prev
    Next
    INDEX
    Explanations

    constant[aq:---my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     évé
    -1.20
    ⿺
    -1.14
    ってみる
    -1.13
    😝
    -1.11
    jelasan
    -1.09
    ⿱
    -1.06
     semoga
    -1.06
     Abends
    -1.05
    🥊
    -1.04
    lxt
    -1.03
    POSITIVE LOGITS
     těchto
    1.20
    这些
    1.16
     gekennzeichnet
    1.14
     avven
    1.08
    這些
    1.07
    quilo
    1.06
     некоторых
    1.05
     ceea
    1.04
    武器
    1.02
    u
    1.02
    Activations Density 0.000%

    No Known Activations