© 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. 11392
    Prev
    Next
    INDEX
    Explanations

    Enrique Serrano names

    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
     rač
    -1.20
     われ
    -1.19
     everyone
    -1.17
    Mű
    -1.17
     its
    -1.16
    ары
    -1.15
     način
    -1.13
     Drž
    -1.10
     those
    -1.08
    áneos
    -1.05
    POSITIVE LOGITS
     here
    1.18
     scorso
    1.05
     aquel
    0.99
     européens
    0.98
    不过是
    0.97
    место
    0.97
    仿佛
    0.95
     dessa
    0.94
     sondern
    0.94
     detenidos
    0.91
    Activations Density 0.000%

    No Known Activations