© 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-262K
    7. 32566
    Prev
    Next
    INDEX
    Explanations

    conditional phrasing

    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_262k_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
     Harp
    0.47
     relentless
    0.47
    It
    0.46
    Бе
    0.45
    gen
    0.45
    genome
    0.44
    ರಾ
    0.44
    恃
    0.43
     marvel
    0.42
    quinolin
    0.42
    POSITIVE LOGITS
     situasi
    0.45
     erneut
    0.45
     거고
    0.44
     කිරීමට
    0.43
    铁路
    0.42
    、【
    0.42
     authorization
    0.40
     भेजना
    0.39
    的重要
    0.39
     penting
    0.39
    Activations Density 0.006%

    No Known Activations