© 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. 34-GEMMASCOPE-RES-131K
    7. 118995
    Prev
    Next
    INDEX
    Explanations

    either express or implied

    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_34/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
    Heroes
    -0.71
     joined
    -0.69
     Änderung
    -0.68
     hens
    -0.66
     samman
    -0.66
    joins
    -0.66
     epithelial
    -0.65
    Wort
    -0.64
     join
    -0.63
    join
    -0.62
    POSITIVE LOGITS
     svilupp
    0.71
    Field
    0.69
     Running
    0.65
     soloist
    0.65
     Distinguished
    0.65
     suicides
    0.64
     avvic
    0.63
    ifero
    0.63
     记
    0.63
     transmissão
    0.63
    Activations Density 0.107%

    No Known Activations