© 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. 44835
    Prev
    Next
    INDEX
    Explanations

    states, conditions, or aspects

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

    rife, Fate, stare, limited

    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
    бер
    0.60
    르
    0.60
    )}}{\
    0.57
    че
    0.56
    לי
    0.56
    ד
    0.56
    ני
    0.55
    י
    0.54
    孱
    0.54
    ק
    0.54
    POSITIVE LOGITS
    0.41
     x
    0.39
     (
    0.38
     Rolling
    0.38
     “
    0.38
     franchising
    0.38
     Oregon
    0.37
     ”
    0.37
     Maine
    0.36
     Pork
    0.36
    Activations Density 0.159%

    No Known Activations