© 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. 13431
    Prev
    Next
    INDEX
    Explanations

    consider when buying

    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
     ReturnVal
    0.47
    ους
    0.47
     смогут
    0.47
     Norse
    0.46
     laude
    0.45
     estejam
    0.44
     полное
    0.44
    ｪ
    0.43
     potranno
    0.43
     estarán
    0.43
    POSITIVE LOGITS
    ‌.
    0.47
    ».
    0.44
    .
    0.42
    শত
    0.40
    decade
    0.39
    बच्च
    0.39
    갤
    0.39
    bas
    0.38
    defining
    0.38
    your
    0.38
    Activations Density 0.003%

    No Known Activations