© 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. 15124
    Prev
    Next
    INDEX
    Explanations

    over on or at

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

    numbers and specific items

    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
    森林
    0.46
    Teste
    0.44
     bosque
    0.44
    ྣ
    0.43
    \"",
    0.42
    င်း
    0.42
    LIB
    0.42
    vě
    0.42
    Declare
    0.41
    ClassObject
    0.41
    POSITIVE LOGITS
     _{(
    0.52
     analyte
    0.50
    alcohol
    0.49
     adopter
    0.47
     desperation
    0.47
     aldehydes
    0.47
    aluminum
    0.46
    acrylate
    0.46
     kerosene
    0.46
    。,
    0.46
    Activations Density 0.000%

    No Known Activations