© 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. 49165
    Prev
    Next
    INDEX
    Explanations

    non-english words and phrases

    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
     Ні
    0.45
     B
    0.44
    피
    0.44
    )->
    0.44
     命令
    0.43
    MIUM
    0.42
     postoperative
    0.42
     Initializes
    0.41
    విద్య
    0.41
     ପ
    0.41
    POSITIVE LOGITS
     এসব
    0.49
    prach
    0.48
     এইসব
    0.47
    These
    0.46
    these
    0.45
    authentic
    0.45
    dealing
    0.45
    pulse
    0.43
    worldly
    0.43
     என்றால்
    0.43
    Activations Density 0.007%

    No Known Activations