© 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. 190688
    Prev
    Next
    INDEX
    Explanations

    describing subsequent actions or states

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

    descriptions and examples

    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
    áte
    0.51
    ış
    0.50
    য়র
    0.50
     DISC
    0.47
    頨
    0.46
    inosa
    0.46
    சியம்
    0.45
    gunakan
    0.45
    ujeme
    0.45
     Torn
    0.45
    POSITIVE LOGITS
     መ
    0.43
    setcounter
    0.41
     depict
    0.41
     সীম
    0.41
     мир
    0.41
     entitle
    0.41
     concedes
    0.41
     softens
    0.41
     Giveen
    0.40
     soften
    0.40
    Activations Density 0.001%

    No Known Activations