© 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. 26877
    Prev
    Next
    INDEX
    Explanations

    common conversational phrases

    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
     clinicians
    0.45
    ინ
    0.44
    Registre
    0.44
     importers
    0.44
    וא
    0.43
     в
    0.42
    את
    0.42
    тет
    0.42
    С
    0.42
     landlords
    0.41
    POSITIVE LOGITS
     même
    0.45
     लेखन
    0.42
     ชีวิต
    0.39
    的研究
    0.39
     Planning
    0.38
    anteen
    0.38
     或
    0.38
     Modeling
    0.37
     Même
    0.37
     Wikipedia
    0.37
    Activations Density 0.004%

    No Known Activations