© 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. 14077
    Prev
    Next
    INDEX
    Explanations

    etwas mehr

    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
     therefore
    0.39
     देखील
    0.38
     seharusnya
    0.38
    也
    0.38
     awalnya
    0.38
    मध्ये
    0.36
     yalnızca
    0.36
    मुळे
    0.36
     estadounidense
    0.36
     infine
    0.35
    POSITIVE LOGITS
    ího
    0.39
     helpen
    0.39
     psyche
    0.37
    czyć
    0.36
     jiné
    0.36
    <unused642>
    0.36
     zá
    0.36
    ouveau
    0.35
     neue
    0.35
    <unused411>
    0.35
    Activations Density 0.028%

    No Known Activations