© 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. 61606
    Prev
    Next
    INDEX
    Explanations

    place on top

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

    signature regions

    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
     podczas
    0.51
     lorsque
    0.49
     Lorsque
    0.48
     wyłącznie
    0.47
     lediglich
    0.45
    のお
    0.45
     أثناء
    0.45
     ዕ
    0.45
     aufgrund
    0.45
     tijdens
    0.45
    POSITIVE LOGITS
    ngModel
    0.45
     THEIR
    0.45
    al
    0.44
    recipes
    0.44
     another
    0.44
    maybe
    0.42
    .......
    0.41
     Offset
    0.41
    VOLUME
    0.41
    ৩৭
    0.41
    Activations Density 0.000%

    No Known Activations