© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86037
    Prev
    Next
    INDEX
    Explanations

    myth, spores, chanterelles, soap film

    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_16_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
    िफ्ट
    0.50
    Ꮁ
    0.50
    𝘯
    0.47
    ấp
    0.45
     bidder
    0.44
    ます
    0.44
     restlessness
    0.44
    られ
    0.43
    ემის
    0.43
     purchaser
    0.42
    POSITIVE LOGITS
    జేపీ
    0.54
     konci
    0.53
    ోంది
    0.48
    ో
    0.48
     الملك
    0.47
     sientes
    0.47
    zej
    0.47
     zehn
    0.47
     য
    0.47
     لكن
    0.47
    Activations Density 0.000%

    No Known Activations