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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11465
    Prev
    Next
    INDEX
    Explanations

    numbers and specific entities

    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
     Για
    -1.30
    殽
    -1.24
    鶫
    -1.20
     its
    -1.16
    presumably
    -1.13
    を開始
    -1.12
    jours
    -1.12
    どういう
    -1.11
     magnifiques
    -1.11
    roxene
    -1.10
    POSITIVE LOGITS
    此外
    1.27
     nahezu
    1.08
    メニューは
    1.05
     verschiedene
    1.05
    大学の
    1.04
    4
    1.02
    5
    0.98
     zahlreiche
    0.97
    3
    0.97
     emphasized
    0.96
    Activations Density 0.028%

    No Known Activations