© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210458
    Prev
    Next
    INDEX
    Explanations

    who are

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

    lack or tragic

    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_31_width_262k_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
     correspondance
    0.45
     telescope
    0.44
     {}>,
    0.43
    2
    0.42
    iri
    0.41
    avelength
    0.41
     estou
    0.41
     なり
    0.41
    ↵
    0.40
    IL
    0.40
    POSITIVE LOGITS
    尼亚克
    0.50
    Numerator
    0.48
     Weaver
    0.46
    𝓊
    0.46
     كيل
    0.46
    𝒹
    0.45
    ម៉
    0.45
    PerRow
    0.44
     resonators
    0.44
     verwendeten
    0.44
    Activations Density 0.001%

    No Known Activations