© 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. 12324
    Prev
    Next
    INDEX
    Explanations

    we, researchers, recent attempts

    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
    knows
    -1.29
    athed
    -1.25
     wasn
    -1.20
    Wasn
    -1.16
    licopter
    -1.13
    llac
    -1.12
    wasn
    -1.05
    ないです
    -1.04
    AnchorStyles
    -1.01
     recommandons
    -1.00
    POSITIVE LOGITS
     recently
    1.21
    īg
    1.02
     chcesz
    1.00
     alcune
    0.98
     several
    0.97
     many
    0.96
     decided
    0.96
     मैंने
    0.96
     algunas
    0.96
     especially
    0.95
    Activations Density 0.060%

    No Known Activations