© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27069
    Prev
    Next
    INDEX
    Explanations

    digging, digestion, digests

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Dedicated
    0.42
    Charged
    0.41
    codiles
    0.41
     अगला
    0.39
    Win
    0.38
     Conductivity
    0.38
    ']
    0.37
     dechlor
    0.37
    瑾
    0.37
     الجنوب
    0.37
    POSITIVE LOGITS
     dig
    0.98
     DIG
    0.93
     Dig
    0.85
    dig
    0.80
    Dig
    0.78
    DIG
    0.77
     Digi
    0.75
     digging
    0.68
     digs
    0.67
     dug
    0.65
    Activations Density 0.010%

    No Known Activations