© 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. 62890
    Prev
    Next
    INDEX
    Explanations

    gift certificate

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

    ( especially )

    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
     cięż
    0.46
     faz
    0.46
     linie
    0.45
     audacious
    0.44
     audacity
    0.44
     oyunc
    0.43
    齑
    0.43
     verzi
    0.43
     tytu
    0.42
     strada
    0.41
    POSITIVE LOGITS
    flipped
    0.49
    retreat
    0.43
    ش
    0.43
    "
    0.43
    #.
    0.42
    probs
    0.42
     phẳng
    0.42
    Queen
    0.41
    {
    0.41
    ▭
    0.41
    Activations Density 0.000%

    No Known Activations