© 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. 41-GEMMASCOPE-2-RES-262K
    7. 100088
    Prev
    Next
    INDEX
    Explanations

    grimlock, crimson, mugen

    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_all/layer_41_width_262k_l0_big
    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
    𝛼
    0.46
    yCoordinate
    0.45
    ≲
    0.45
     salariés
    0.44
    𝜌
    0.44
    ೊಳ್ಳ
    0.42
    玉
    0.42
    センサー
    0.42
    ဍ
    0.42
     हाइट
    0.41
    POSITIVE LOGITS
     terrible
    0.46
    ussen
    0.43
     범
    0.42
     clickable
    0.41
     cardinal
    0.40
     crimen
    0.39
     fatal
    0.38
     reve
    0.38
     horrible
    0.38
    remen
    0.38
    Activations Density 0.000%

    No Known Activations