© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 124422
    Prev
    Next
    INDEX
    Explanations

    skillful chiropractor

    np_acts-logits-general · gemini-2.5-flash-lite

    programs and behaviors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nocześnie
    0.47
    म्ब
    0.46
    𝗞
    0.45
    ك
    0.44
    𝐤
    0.44
     బా
    0.43
     ні
    0.43
     dropping
    0.43
     ሀ
    0.43
     Findlay
    0.42
    POSITIVE LOGITS
    पित
    0.49
    Todo
    0.49
    ઠી
    0.48
    }
    0.48
    cinoma
    0.46
     Todo
    0.46
    育
    0.46
    초
    0.45
    i
    0.45
     animations
    0.44
    Activations Density 0.005%

    No Known Activations