© 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. 51569
    Prev
    Next
    INDEX
    Explanations

    to work or invest

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

    gear, scan, resume, footage, return

    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
    xc
    0.50
    +,
    0.46
     giri
    0.45
    :,
    0.45
    لی
    0.45
    ],
    0.43
    *,
    0.42
     चतु
    0.42
     signature
    0.42
    ,…
    0.42
    POSITIVE LOGITS
    лай
    0.47
    気軽
    0.47
    骄
    0.47
    тур
    0.46
    盔
    0.45
    府中
    0.45
    lion
    0.45
    illés
    0.45
     absences
    0.44
    ни
    0.44
    Activations Density 0.000%

    No Known Activations