© 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. 105703
    Prev
    Next
    INDEX
    Explanations

    IF condition

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

    prompt lead

    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
    쓴
    0.49
    [
    0.47
    adin
    0.46
     Medications
    0.46
     Colours
    0.45
     Lint
    0.44
     Colors
    0.44
     New
    0.43
    akad
    0.42
    Annot
    0.42
    POSITIVE LOGITS
     জার্মান
    0.50
     prized
    0.48
     سي
    0.46
    ه
    0.45
     মর্টার
    0.44
     حي
    0.44
    ပြန်
    0.43
    leadsto
    0.43
    ን
    0.43
     beliebt
    0.43
    Activations Density 0.000%

    No Known Activations