© 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. 26753
    Prev
    Next
    INDEX
    Explanations

    as is disclaimer

    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
    წ
    0.46
    C
    0.46
    槸
    0.45
    ህ
    0.44
    ამ
    0.44
    ט
    0.43
    說
    0.43
    edges
    0.43
    ्वती
    0.43
    Y
    0.41
    POSITIVE LOGITS
     tanpa
    0.57
     без
    0.55
     without
    0.54
     unmodified
    0.51
     unchanged
    0.50
     الحال
    0.48
    ktan
    0.46
     അവസ്ഥ
    0.46
     senza
    0.45
     unfiltered
    0.45
    Activations Density 0.000%

    No Known Activations