© 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. 239380
    Prev
    Next
    INDEX
    Explanations

    replacement physical compete stuffed in

    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
    他
    0.49
     również
    0.47
     পাওয়া
    0.47
    看见
    0.45
     pozost
    0.45
     posing
    0.45
     zau
    0.45
     wraz
    0.45
     posed
    0.44
     questioning
    0.44
    POSITIVE LOGITS
    _{,
    0.50
    gradation
    0.45
    lof
    0.44
    ргани
    0.43
    纯
    0.42
    ริญ
    0.42
    ordinary
    0.41
    Postfix
    0.40
    aton
    0.40
    iare
    0.40
    Activations Density 0.003%

    No Known Activations