© 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. 30769
    Prev
    Next
    INDEX
    Explanations

    quantities following "about"

    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
    8
    0.45
    9
    0.44
    6
    0.43
     型
    0.40
    7
    0.40
     tenfold
    0.39
    3
    0.38
    schemas
    0.37
     rarement
    0.37
    2
    0.37
    POSITIVE LOGITS
     aforementioned
    0.42
    স্তের
    0.40
     фараз
    0.40
     afore
    0.39
    VISED
    0.38
    asional
    0.37
     आरोप
    0.35
    城乡
    0.35
     کھیلو
    0.35
     Shining
    0.35
    Activations Density 0.001%

    No Known Activations