© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12199
    Prev
    Next
    INDEX
    Explanations

    import from

    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
     even
    -1.23
     only
    -1.22
     now
    -1.16
     becomes
    -1.15
     to
    -1.15
     analysis
    -1.15
     when
    -1.13
     two
    -1.11
     started
    -1.10
     increased
    -1.10
    POSITIVE LOGITS
     célè
    1.23
    aimeJ
    1.19
    honestly
    1.17
     éché
    1.16
     symptômes
    1.14
    わけです
    1.12
     repuesto
    1.11
    ፨
    1.10
     siè
    1.09
    すっ
    1.09
    Activations Density 0.004%

    No Known Activations