© 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. 12225
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
     but
    -1.32
    couverte
    -1.09
    uevos
    -1.01
     Unmarshal
    -1.00
     algunas
    -1.00
     while
    -0.99
     particularly
    -0.98
    ゅう
    -0.97
    utusan
    -0.97
    RIOS
    -0.96
    POSITIVE LOGITS
     filosof
    1.34
     kasa
    1.23
    unlike
    1.20
     faktiskt
    1.20
     maksi
    1.19
     vélos
    1.18
     vrais
    1.18
     our
    1.16
     unlike
    1.15
     bezpośrednio
    1.15
    Activations Density 0.048%

    No Known Activations