© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 136577
    Prev
    Next
    INDEX
    Explanations

    description of habitat

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

    web design or website product

    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
     angr
    0.46
    _{*}
    0.44
    ULA
    0.43
    工资
    0.42
    ไหน
    0.42
     його
    0.41
     fm
    0.41
     gurus
    0.40
     boundedness
    0.40
    爷爷
    0.40
    POSITIVE LOGITS
    on
    0.73
    a
    0.52
    have
    0.51
    de
    0.48
    ivant
    0.48
    normalize
    0.46
    eliminate
    0.46
    return
    0.46
    peek
    0.46
    Patent
    0.45
    Activations Density 0.000%

    No Known Activations