© 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. 246471
    Prev
    Next
    INDEX
    Explanations

    . and

    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
     kleinere
    0.59
     հ
    0.52
     kiz
    0.50
    ின்
    0.49
    ሳይ
    0.48
    クマ
    0.48
    кна
    0.48
     България
    0.48
     jiné
    0.47
     ល
    0.47
    POSITIVE LOGITS
    Q
    0.51
     MOV
    0.48
    ston
    0.47
     согласо
    0.47
    d
    0.44
    spaces
    0.42
    ﯾ
    0.42
     intrans
    0.41
     remar
    0.41
     Savannah
    0.41
    Activations Density 0.001%

    No Known Activations