© 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. 101574
    Prev
    Next
    INDEX
    Explanations

    great, most, another

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

    cannot directly create visuals

    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
     Aś
    0.49
     Phát
    0.48
    ட்கள்
    0.47
    +"\
    0.46
    亠
    0.46
    POA
    0.46
    ỏi
    0.44
     одно
    0.44
    گو
    0.44
     Але
    0.44
    POSITIVE LOGITS
     WINTER
    0.48
     to
    0.46
     memper
    0.45
    3
    0.43
     COUNTRY
    0.43
    2
    0.43
    Winter
    0.43
    ς
    0.42
    িয়া
    0.42
    ᔨ
    0.42
    Activations Density 0.000%

    No Known Activations