© 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. 36880
    Prev
    Next
    INDEX
    Explanations

    stationary or stopping

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

    lists of items

    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
    蹒
    0.43
     Geografia
    0.42
    धिकारी
    0.41
     Hypothesis
    0.41
    peptide
    0.40
     ঘি
    0.40
    braith
    0.39
    பால
    0.38
    往前
    0.38
    莪
    0.37
    POSITIVE LOGITS
     stationary
    0.44
     stopp
    0.43
     terminal
    0.42
     Stopping
    0.39
     stoppage
    0.39
    หยุด
    0.38
     sedentary
    0.37
     întâ
    0.37
     immobilization
    0.36
    Stopping
    0.35
    Activations Density 0.139%

    No Known Activations