© 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. 74893
    Prev
    Next
    INDEX
    Explanations

    welcome all contributorsLookinglarge utilityworth notingbe deprivedno problemweb page

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

    confidence and horns

    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
    ursery
    0.43
    َّ
    0.43
    Alles
    0.43
    భా
    0.42
    ortes
    0.42
    膿
    0.42
    با
    0.42
    formes
    0.41
     Dies
    0.41
    ictionaries
    0.41
    POSITIVE LOGITS
     kapan
    0.49
     transmittance
    0.47
     کیلوم
    0.46
     ACF
    0.45
     sahabat
    0.45
     lensa
    0.45
     thermostat
    0.45
    ⱪ
    0.45
    TARGETTING
    0.43
     fluorescence
    0.43
    Activations Density 0.001%

    No Known Activations