© 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. 117403
    Prev
    Next
    INDEX
    Explanations

    Personal interests, pretty much

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

    facial recognition technology

    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
    k
    0.55
    씁
    0.52
     రా
    0.50
    ي
    0.50
    g
    0.48
     சம்பவம்
    0.47
     بك
    0.47
    ház
    0.47
    STM
    0.47
    z
    0.47
    POSITIVE LOGITS
     designing
    0.43
     courants
    0.43
    ောက်
    0.42
     Lors
    0.42
    クサ
    0.41
     проекту
    0.41
    ன்மையான
    0.41
    ంచి
    0.41
     femoral
    0.41
    きれい
    0.41
    Activations Density 0.000%

    No Known Activations