© 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. 102545
    Prev
    Next
    INDEX
    Explanations

    "Collapsed" =

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

    indexing and assignment

    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
    ()){
    0.50
     работаю
    0.49
    所で
    0.48
     которому
    0.45
    ']."
    0.45
    ியின்
    0.44
    ⸨
    0.43
    ्याच्या
    0.42
    ്യമ
    0.41
    [],
    0.41
    POSITIVE LOGITS
     =
    0.75
     is
    0.63
     ialah
    0.63
     was
    0.62
     are
    0.55
     adalah
    0.55
    =
    0.54
     were
    0.52
     $=
    0.52
    は
    0.52
    Activations Density 0.001%

    No Known Activations