© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140244
    Prev
    Next
    INDEX
    Explanations

    traditionally credited, linear regulator

    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
    1
    0.60
    áne
    0.60
    ane
    0.59
    9
    0.57
    3
    0.55
    ap
    0.54
    .
    0.54
    8
    0.53
    NI
    0.53
    -
    0.52
    POSITIVE LOGITS
     prostit
    0.59
     agreg
    0.56
     didik
    0.56
     hizo
    0.55
     gui
    0.54
     Guillermo
    0.54
     Pasha
    0.54
    ونکی
    0.54
     paramet
    0.53
     ആയി
    0.53
    Activations Density 0.000%

    No Known Activations