Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11830
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     on
    -1.15
     MessageBoxIcon
    -1.10
     he
    -1.06
    centerTitle
    -1.05
     və
    -1.05
     their
    -1.02
     to
    -1.02
    рио
    -1.02
    vello
    -1.00
    惫
    -1.00
    POSITIVE LOGITS
    ou
    1.15
     gedachten
    1.12
     européens
    1.12
     erhi
    1.11
     letzten
    1.09
    ,..
    1.08
     Vnd
    1.06
     bewegt
    1.05
     américains
    1.05
     weihnachten
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.