© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14166
    Prev
    Next
    INDEX
    Explanations

    concepts in diverse contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    町の
    0.50
     χαρακτη
    0.45
    contrad
    0.43
    本の
    0.42
    irittura
    0.42
    ⟨
    0.41
     rest
    0.40
     tota
    0.40
    β
    0.39
     Eulerian
    0.39
    POSITIVE LOGITS
     équipements
    0.49
     erhält
    0.45
    燊
    0.44
    ismar
    0.44
    ipun
    0.43
     sommer
    0.43
     bør
    0.43
     været
    0.42
    फल
    0.42
    rikt
    0.41
    Activations Density 0.000%

    No Known Activations