© 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. 45024
    Prev
    Next
    INDEX
    Explanations

    tolerances

    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
    та
    0.73
    red
    0.70
    о
    0.64
    on
    0.64
    的問題
    0.63
    lin
    0.59
    ressed
    0.59
    поли
    0.59
    V
    0.57
    now
    0.57
    POSITIVE LOGITS
     envo
    0.57
     biel
    0.57
     vaste
    0.55
     ridd
    0.55
     leit
    0.55
    <tbody>
    0.54
     Trident
    0.54
     alve
    0.54
     pillars
    0.53
    (/(
    0.53
    Activations Density 0.000%

    No Known Activations