© 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. 131185
    Prev
    Next
    INDEX
    Explanations

    today's updates or events

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

    stomatal and churn rates

    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
    弇
    0.53
     yanında
    0.47
    setTextColor
    0.45
    សិក
    0.45
     കണ്ടെ
    0.44
     массив
    0.44
    ामो
    0.44
    lüğü
    0.44
     معلوم
    0.44
    ŧ
    0.44
    POSITIVE LOGITS
    -
    0.51
     revolution
    0.47
    0.46
     smartphones
    0.46
     esports
    0.44
     Paramount
    0.43
     Artists
    0.42
     GeForce
    0.42
     Sapphire
    0.41
     metaverse
    0.41
    Activations Density 0.000%

    No Known Activations