© 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. 7994
    Prev
    Next
    INDEX
    Explanations

    except

    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
    λλην
    0.41
    oniazid
    0.39
    친
    0.38
    显然
    0.37
     metastable
    0.37
    зів
    0.36
     sonst
    0.35
    ׃
    0.35
     tentu
    0.35
     tetap
    0.35
    POSITIVE LOGITS
     except
    1.17
     Except
    1.03
    except
    0.98
    Except
    0.97
     excepto
    0.91
     EXCEPT
    0.86
    只不过
    0.85
     sauf
    0.77
     minus
    0.73
     excepting
    0.72
    Activations Density 0.178%

    No Known Activations