© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140339
    Prev
    Next
    INDEX
    Explanations

    Bob Ross and Olaf Scholz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    3
    0.67
    ال
    0.65
    א
    0.59
     as
    0.53
    어
    0.53
    ३
    0.53
     +
    0.52
    미
    0.52
    아
    0.52
     아
    0.52
    POSITIVE LOGITS
    LockButton
    0.52
    ائيل
    0.51
     rousing
    0.51
    werken
    0.51
     WordPerfect
    0.51
    etric
    0.50
    ಮಂತ್ರಿ
    0.50
     Hov
    0.50
    ués
    0.50
     Frankel
    0.50
    Activations Density 0.000%

    No Known Activations