© 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. 236560
    Prev
    Next
    INDEX
    Explanations

    contact and organization information

    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
     parable
    0.48
     anthrac
    0.48
     Worry
    0.47
    Ẹ
    0.44
    }\|\
    0.43
     ಜನರು
    0.43
     fright
    0.43
    ారు
    0.43
     जगत
    0.42
     urged
    0.41
    POSITIVE LOGITS
    maybe
    0.48
    氾
    0.47
    transition
    0.46
    ajar
    0.45
    过渡
    0.45
    dl
    0.45
    2
    0.44
     Shazam
    0.44
     развитию
    0.44
    fft
    0.43
    Activations Density 0.001%

    No Known Activations