© 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. 142894
    Prev
    Next
    INDEX
    Explanations

    digital space

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

    key attributes or differences

    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
    亽
    0.59
    чнай
    0.54
    ыр
    0.53
    นิยม
    0.53
    िट
    0.51
    ਿੰ
    0.50
    ཋ
    0.50
    लै
    0.49
    気を
    0.48
    ╮
    0.48
    POSITIVE LOGITS
     c
    0.63
    ali
    0.55
     f
    0.54
    az
    0.53
    acc
    0.53
     l
    0.52
     j
    0.52
    ata
    0.52
     i
    0.52
    odu
    0.52
    Activations Density 0.000%

    No Known Activations