© 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. 12261
    Prev
    Next
    INDEX
    Explanations

    seems like everyone or everything

    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
     bluzka
    -1.11
     meditación
    -1.07
     теперь
    -1.00
    écution
    -0.99
    飛行機
    -0.97
     now
    -0.97
     发表于
    -0.96
    ExtendWith
    -0.96
    GEBURTS
    -0.94
    𝟗
    -0.94
    POSITIVE LOGITS
     every
    1.52
     each
    1.25
     interminable
    1.03
     poulet
    1.03
     somehow
    1.00
     inexhaustible
    0.98
     bereiken
    0.98
     chaque
    0.96
     everything
    0.92
     endless
    0.92
    Activations Density 0.026%

    No Known Activations