© 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. 115674
    Prev
    Next
    INDEX
    Explanations

    free and accompanied

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

    free, alternatives, itself

    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
    聶
    0.46
    DebuggingMode
    0.46
    മ്ബ
    0.45
    BuildAction
    0.44
    Shelf
    0.44
    ဘာ
    0.44
    Solve
    0.43
     omg
    0.43
    Decoder
    0.43
     宋
    0.43
    POSITIVE LOGITS
     দুর
    0.44
     hilly
    0.44
     pénétr
    0.44
     buzzing
    0.43
     त
    0.43
     on
    0.42
     ರಿಂದ
    0.42
     ಒಂದು
    0.42
     waste
    0.42
    کا
    0.41
    Activations Density 0.000%

    No Known Activations