© 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. 246036
    Prev
    Next
    INDEX
    Explanations

    Cheddar Ragu

    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
     ergän
    0.54
     darüber
    0.48
    幸
    0.46
     bereits
    0.46
     trừ
    0.46
     hingegen
    0.46
     сопровожда
    0.45
     familial
    0.45
     Naj
    0.45
     Künstler
    0.44
    POSITIVE LOGITS
    𝗖
    0.48
    toothpaste
    0.46
    गित
    0.46
    ooo
    0.45
    वस्था
    0.45
    ng
    0.45
    ibh
    0.45
    rrrr
    0.44
    j
    0.44
    สภาพ
    0.44
    Activations Density 0.000%

    No Known Activations