© 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. 173981
    Prev
    Next
    INDEX
    Explanations

    gazelle

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

    have been released

    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
     интерпре
    0.59
     ширина
    0.54
     வழக்கு
    0.53
    ᕈ
    0.53
     места
    0.52
     évo
    0.51
     русского
    0.51
     współprac
    0.51
    ጕ
    0.51
     уви
    0.51
    POSITIVE LOGITS
    YC
    0.47
     decimal
    0.43
    BC
    0.43
    aS
    0.43
     Equations
    0.43
     BC
    0.42
    Approach
    0.42
    Access
    0.41
    Af
    0.40
    Info
    0.40
    Activations Density 0.000%

    No Known Activations