© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1537
    Prev
    Next
    INDEX
    Explanations

    javascript file paths

    np_acts-logits-general · gemini-2.5-flash-lite

    import pandas and numpy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ⴌ
    0.42
    ంచరీలు
    0.41
    蹬
    0.41
    <unused40>
    0.40
    𒇻
    0.39
     सुनेंरोक
    0.39
    瓈
    0.39
    叁章
    0.38
    帏
    0.38
    皰
    0.38
    POSITIVE LOGITS
    .*
    0.72
    .*;
    0.72
    _
    0.65
    ;
    0.62
    .
    0.60
    ,
    0.56
    ._
    0.56
    utils
    0.51
    -
    0.50
    x
    0.49
    Activations Density 0.017%

    No Known Activations