© 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. 162823
    Prev
    Next
    INDEX
    Explanations

    notice to issue

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

    past tense followed by gerund

    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
    \})
    0.48
    下来
    0.46
    雬
    0.45
     เฟ
    0.45
    ."))
    0.45
     PHE
    0.44
     अंक
    0.44
    immä
    0.43
     ውጤ
    0.43
    是真的
    0.43
    POSITIVE LOGITS
    ホワイト
    0.55
    baz
    0.52
    Lorem
    0.50
    White
    0.50
    Baz
    0.50
    gov
    0.48
     webinars
    0.48
    LGBT
    0.47
    この
    0.46
     a
    0.46
    Activations Density 0.001%

    No Known Activations