© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24704
    Prev
    Next
    INDEX
    Explanations

    objects, crescent, liquid, disable, even

    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
    Negative Logits
     चिल्
    0.47
    ន្តែ
    0.45
    PanelView
    0.44
    Powell
    0.43
     ανθ
    0.42
    xico
    0.41
     తరువాత
    0.41
    洪
    0.41
    暄
    0.41
    studentRecord
    0.40
    POSITIVE LOGITS
    ')).
    0.44
    peanut
    0.44
     peanut
    0.40
    ebox
    0.38
    pek
    0.36
    wins
    0.36
    peach
    0.35
     (_
    0.35
     peach
    0.35
     grips
    0.35
    Activations Density 0.000%

    No Known Activations