© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1907
    Prev
    Next
    INDEX
    Explanations

    titles and descriptions

    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_40_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
    𒅅
    0.37
    tBleStatus
    0.37
    پلز
    0.36
    Flicky
    0.36
    ائیگی
    0.35
    昅
    0.35
     کھیلو
    0.34
    ټبال
    0.34
     হইয়৷
    0.34
    تباينه
    0.34
    POSITIVE LOGITS
     of
    0.52
     the
    0.49
     without
    0.47
    s
    0.47
     and
    0.45
    ’
    0.44
    -
    0.44
     to
    0.43
    7
    0.42
     O
    0.42
    Activations Density 0.000%

    No Known Activations