© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 257623
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    comboBox
    0.52
    ron
    0.49
    ibilit
    0.48
    itud
    0.48
    yw
    0.48
    鹰
    0.47
    localPosition
    0.47
    鸟
    0.46
    komst
    0.44
    othe
    0.44
    POSITIVE LOGITS
     pleated
    0.47
     pero
    0.46
     токси
    0.46
     toks
    0.46
     toxicity
    0.45
     PLEASE
    0.45
     intenso
    0.44
     mashed
    0.44
    اما
    0.43
    Ghana
    0.42
    Activations Density 0.002%

    No Known Activations