© 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. 236696
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    橇
    0.50
    콘
    0.48
    ()));
    0.47
    irr
    0.46
     کوي
    0.45
    abase
    0.45
    ì
    0.45
    í
    0.44
    four
    0.44
    ι
    0.44
    POSITIVE LOGITS
     carcinomas
    0.50
    BIUM
    0.49
     reu
    0.47
     یا
    0.46
     অথবা
    0.45
    esthetics
    0.45
     naughty
    0.44
     oddly
    0.43
    褪
    0.43
     babys
    0.43
    Activations Density 0.001%

    No Known Activations