© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62725
    Prev
    Next
    INDEX
    Explanations

    sighting of

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

    visibility, functionality, twisted

    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
    um
    0.46
    设定
    0.43
    ри
    0.42
    </tfoot>
    0.41
    ↡
    0.41
    an
    0.40
    ár
    0.40
    en
    0.38
    必須
    0.38
    ენი
    0.38
    POSITIVE LOGITS
     veya
    0.54
     ⿰
    0.54
     pyaar
    0.52
     allora
    0.51
     potenza
    0.51
     considerazione
    0.50
     manifiesta
    0.48
     courants
    0.48
     trafic
    0.48
     esempi
    0.48
    Activations Density 0.000%

    No Known Activations