© 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. 26006
    Prev
    Next
    INDEX
    Explanations

    them off, bill total

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

    specific actions and conditions

    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
     Company
    0.45
    '
    0.44
    ">';
    0.42
     olma
    0.42
    -
    0.42
    "><
    0.42
     visionary
    0.41
     humanity
    0.41
     COMPANY
    0.40
    ‌‌
    0.40
    POSITIVE LOGITS
     அதிகமாக
    0.53
    ckså
    0.48
     பெரும்பாலான
    0.46
     반지름
    0.45
     ប៉ុ
    0.45
     특히
    0.44
    abhäng
    0.42
    unächst
    0.42
    например
    0.42
    齦
    0.42
    Activations Density 0.000%

    No Known Activations