© 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. 10872
    Prev
    Next
    INDEX
    Explanations

    absolute value or | symbol

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

    absolute value

    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
    WATER
    0.56
     पानी
    0.54
    ન્યા
    0.53
    baptism
    0.52
     vodu
    0.52
    󠁷
    0.51
    라인
    0.50
    chairs
    0.49
     மருத்து
    0.49
     চূ
    0.49
    POSITIVE LOGITS
     ∣
    0.55
    =|
    0.52
     eisen
    0.52
     ABS
    0.50
    ;|
    0.50
     fabs
    0.50
    gt
    0.48
     abs
    0.48
     (|
    0.48
     Eisenhower
    0.46
    Activations Density 0.006%

    No Known Activations