© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3508
    Prev
    Next
    INDEX
    Explanations

    separating items in lists

    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_31_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
    葢
    0.46
    Trajectories
    0.43
    $&$-
    0.42
     يت
    0.41
    ቈ
    0.41
    BleStatus
    0.40
    CardArray
    0.40
    בו
    0.39
     فِي
    0.39
    DOUT
    0.39
    POSITIVE LOGITS
     ,
    0.50
    also
    0.50
    plus
    0.49
    ↵
    0.48
    again
    0.48
    ↵↵
    0.48
     ;
    0.48
     Again
    0.46
     again
    0.46
    ini
    0.45
    Activations Density 0.378%

    No Known Activations