© 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. 97910
    Prev
    Next
    INDEX
    Explanations

    delicious dessert, good practice, anyone voting

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

    explaining capabilities or states

    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
     inférieure
    0.51
     Status
    0.50
     Erschein
    0.47
     partielle
    0.47
     Bldg
    0.46
     நடக்க
    0.46
    s
    0.46
     خفی
    0.46
     semakin
    0.45
     Kauf
    0.44
    POSITIVE LOGITS
    沖
    0.47
    નમાં
    0.45
    ismatic
    0.43
    倉
    0.42
    READER
    0.42
    ковым
    0.42
    賓
    0.42
    BtnFill
    0.41
    imba
    0.41
    тном
    0.41
    Activations Density 0.000%

    No Known Activations