© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 59100
    Prev
    Next
    INDEX
    Explanations

    small quantities or adjustments

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

    rare and few occurrences

    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
     Sonny
    0.42
    fæ
    0.41
     "*****
    0.40
    ต์
    0.40
     Beaufort
    0.40
    inelli
    0.39
     Buddy
    0.39
     Zugang
    0.39
    ∕
    0.39
     Stry
    0.39
    POSITIVE LOGITS
     tweaks
    0.50
    واحد
    0.47
     tweaked
    0.44
    GED
    0.43
    мора
    0.43
    ξη
    0.43
     overwhel
    0.42
     megs
    0.42
    RANGER
    0.42
    STATIC
    0.41
    Activations Density 0.000%

    No Known Activations