© 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. 39331
    Prev
    Next
    INDEX
    Explanations

    medical wellness and angina

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

    unlock new, allow yourself

    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
    f
    0.63
    hen
    0.53
    HEN
    0.52
    ọ
    0.50
    WORTH
    0.49
     efectivamente
    0.48
    em
    0.47
    Fs
    0.46
     amu
    0.46
     độ
    0.45
    POSITIVE LOGITS
     batt
    0.47
    霹
    0.44
     Civic
    0.43
    Wellness
    0.42
     DCs
    0.42
     Wellness
    0.41
     बिज
    0.41
    batt
    0.41
     pico
    0.41
     wellness
    0.40
    Activations Density 0.000%

    No Known Activations