© 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-65K
    7. 17062
    Prev
    Next
    INDEX
    Explanations

    sensory, costs, leadership, volatile, lives, validation, mate, paradox, prompts

    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_65k_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
     Microscopy
    0.40
     r
    0.38
    మ్
    0.37
    ώ
    0.37
     urllib
    0.37
    ড়
    0.36
    ur
    0.36
    λ
    0.36
    ্স
    0.36
    tailwindcss
    0.35
    POSITIVE LOGITS
    ).
    0.49
     alguma
    0.47
     yukarı
    0.47
     powin
    0.43
     quelqu
    0.41
    ؟
    0.40
    )،
    0.40
     powinno
    0.40
     dolores
    0.39
     That
    0.38
    Activations Density 0.165%

    No Known Activations