© 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. 3886
    Prev
    Next
    INDEX
    Explanations

    collaborating, quicker, repeatable, share

    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
     современном
    0.45
    পাতালে
    0.44
    侘
    0.44
    DVD
    0.44
     novelty
    0.44
    ವರಿಗೆ
    0.44
     வீர
    0.43
    тове
    0.43
    ordial
    0.42
    چم
    0.42
    POSITIVE LOGITS
    ని
    0.53
    ض
    0.51
     η
    0.45
    S
    0.44
     aż
    0.42
    G
    0.42
    ن
    0.42
     si
    0.42
    取消
    0.42
     naf
    0.42
    Activations Density 0.001%

    No Known Activations