© 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. 137487
    Prev
    Next
    INDEX
    Explanations

    kick off, kick out, slow of

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

    python plotting libraries

    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
    য্
    0.45
     unruly
    0.44
    இத
    0.44
    |)
    0.43
    केजी
    0.41
    луй
    0.41
    زالة
    0.41
    |।
    0.40
    Dried
    0.40
     transcripts
    0.39
    POSITIVE LOGITS
     거고
    0.51
    to
    0.46
    APPRO
    0.45
    COLOR
    0.44
    color
    0.44
    gradient
    0.43
    tint
    0.43
    ATING
    0.43
     स्टूडियो
    0.43
     MEDIA
    0.42
    Activations Density 0.005%

    No Known Activations