© 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. 168725
    Prev
    Next
    INDEX
    Explanations

    life line, brings outweighs, spent on

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

    creates a, will try, there exists

    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
     furiously
    0.46
    뻣
    0.45
     sitten
    0.45
    ්‍යා
    0.45
    asso
    0.44
     then
    0.42
    Compiled
    0.41
    Didn
    0.41
    ☼
    0.40
     quickly
    0.40
    POSITIVE LOGITS
     tappa
    0.47
    ṅ
    0.47
     ਆ
    0.45
    rrbracket
    0.45
    रण
    0.44
    TRANS
    0.44
    哒
    0.44
    llbracket
    0.44
     qay
    0.44
     ഉണ്ട്
    0.44
    Activations Density 0.002%

    No Known Activations