© 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. 95737
    Prev
    Next
    INDEX
    Explanations

    sanitation shaver

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

    good sign, enemy of progress

    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
    ab
    0.53
    plans
    0.52
    B
    0.46
     ಹೊಂದಿ
    0.46
     …”
    0.45
    radi
    0.45
    বিএন
    0.45
    HAS
    0.45
    op
    0.44
     ಕರಿಬೇವಿನ
    0.44
    POSITIVE LOGITS
    ؛
    0.51
     Sanitation
    0.45
     shaver
    0.45
     ordinarily
    0.44
     cyclohex
    0.44
    ；
    0.43
     mechanical
    0.43
     necrosis
    0.43
    шке
    0.43
     chronograph
    0.43
    Activations Density 0.001%

    No Known Activations