© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167557
    Prev
    Next
    INDEX
    Explanations

    spatial prepositions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    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
     того
    0.98
     quello
    0.97
     đó
    0.95
     itu
    0.86
    那
    0.78
     toho
    0.75
     aquilo
    0.74
     ذلك
    0.74
     Đó
    0.70
     ciò
    0.70
    POSITIVE LOGITS
    큼
    0.41
    লিক
    0.38
    pls
    0.38
     backend
    0.37
    cue
    0.36
     punctuation
    0.36
    ništ
    0.35
    図柄
    0.35
    ancers
    0.33
    JW
    0.33
    Activations Density 0.001%

    No Known Activations