© 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. 147908
    Prev
    Next
    INDEX
    Explanations

    keywords preceding punctuation

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

    activations

    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
    0.58
     decreases
    0.53
     splits
    0.49
    ']},
    0.46
     IActionResult
    0.46
     restores
    0.45
     curls
    0.45
     fissures
    0.45
    ’.
    0.44
     reverses
    0.44
    POSITIVE LOGITS
    نائ
    0.49
    کنش
    0.49
    မှတ်
    0.48
    strand
    0.48
    کت
    0.47
     বিএন
    0.46
    သည့်
    0.45
    ક્
    0.45
    ﹰ
    0.45
     Mặt
    0.44
    Activations Density 0.000%

    No Known Activations