© 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. 7253
    Prev
    Next
    INDEX
    Explanations

    license or compatible

    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
    ai
    0.37
     CV
    0.37
     mortals
    0.35
    rivastava
    0.34
     unmanned
    0.33
    į
    0.33
     curriculum
    0.33
    েকে
    0.33
     ملي
    0.33
     ฝึก
    0.33
    POSITIVE LOGITS
     kompat
    0.47
     WHICH
    0.45
    CLUDES
    0.45
    兼容
    0.44
     versie
    0.43
     ALSO
    0.42
     compatible
    0.41
     Compatibility
    0.39
     compatibility
    0.38
    阐
    0.38
    Activations Density 0.004%

    No Known Activations