© 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. 160960
    Prev
    Next
    INDEX
    Explanations

    dates, video, bin, running, 3, language

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

    then combine, promised to

    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
     you
    0.44
    بور
    0.44
    ंक
    0.43
    س
    0.43
    سب
    0.42
     of
    0.42
    猝
    0.42
    दि
    0.41
    या
    0.41
     Cellular
    0.41
    POSITIVE LOGITS
     проще
    0.52
     discontinuities
    0.49
     atheros
    0.48
    Preprocessor
    0.47
    AGON
    0.46
    époque
    0.46
    vDash
    0.45
     MODELS
    0.44
    ^{\#}\
    0.44
    ʔ
    0.44
    Activations Density 0.000%

    No Known Activations