© 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. 12906
    Prev
    Next
    INDEX
    Explanations

    rat **and**

    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
     Craig
    0.52
    uar
    0.45
     農
    0.44
     for
    0.43
    at
    0.43
    is
    0.42
    Craig
    0.42
    },
    0.42
    van
    0.41
     pattern
    0.41
    POSITIVE LOGITS
    醗
    0.47
    ത്താ
    0.46
     کئی
    0.46
    悩
    0.46
    璨
    0.46
    issime
    0.45
    pipelines
    0.45
    ٹی
    0.44
    ྥ
    0.44
     ہمارے
    0.44
    Activations Density 0.007%

    No Known Activations