© 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. 10-GEMMASCOPE-RES-131K
    7. 734
    Prev
    Next
    INDEX
    Explanations

    though

    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_10/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
     a
    -1.67
    इटम
    -1.63
     this
    -1.59
     it
    -1.56
    肫
    -1.55
     each
    -1.53
     thier
    -1.50
    ⟝
    -1.44
    *****/
    -1.44
    lgari
    -1.41
    POSITIVE LOGITS
    3
    1.84
    5
    1.69
    4
    1.68
    6
    1.65
    0
    1.65
    8
    1.61
    And
    1.60
    <bos>
    1.58
    l
    1.48
     hebdomada
    1.47
    Activations Density 0.021%

    No Known Activations