© 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. 43125
    Prev
    Next
    INDEX
    Explanations

    order or takeout

    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
     colorless
    0.65
     Å
    0.60
     and
    0.57
     tipped
    0.57
     catalyzed
    0.57
    ো
    0.55
     The
    0.54
     А
    0.54
     С
    0.54
     oxidizing
    0.53
    POSITIVE LOGITS
    滹
    0.55
    parvec
    0.53
    ❾
    0.53
    anner
    0.53
    стре
    0.53
    ститут
    0.53
    豢
    0.53
    percayaan
    0.52
     अनुदान
    0.52
    efficiencies
    0.51
    Activations Density 0.000%

    No Known Activations