© 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. 162803
    Prev
    Next
    INDEX
    Explanations

    alternatives or options

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

    alternative ideas or methods

    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
     eaten
    0.51
     polít
    0.46
     accentuated
    0.45
     evaded
    0.44
    consumed
    0.44
    踟
    0.42
    ἵ
    0.42
    ٰذا
    0.41
    itorio
    0.41
    omé
    0.41
    POSITIVE LOGITS
     veya
    0.53
     یا
    0.49
     или
    0.49
     किंवा
    0.48
     kullanılan
    0.48
    하거나
    0.46
     또는
    0.46
    Derivative
    0.46
     or
    0.45
     new
    0.45
    Activations Density 0.003%

    No Known Activations