© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3414
    Prev
    Next
    INDEX
    Explanations

    organization detached impulses expenses facts

    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
    in
    0.65
    ing
    0.48
    il
    0.48
    is
    0.47
    er
    0.46
    t
    0.44
    it
    0.44
    í
    0.42
     with
    0.42
     to
    0.42
    POSITIVE LOGITS
    ىل
    0.35
    说道
    0.34
    笑道
    0.33
    ﮐ
    0.33
     السنوات
    0.31
    togel
    0.31
     റിപ്പോ
    0.31
    lässlich
    0.31
    ߋ
    0.30
    Jogador
    0.30
    Activations Density 0.009%

    No Known Activations