© 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. 101091
    Prev
    Next
    INDEX
    Explanations

    level of commitment or comfort

    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
    номо
    0.50
    貅
    0.49
    ко
    0.48
    疲
    0.48
    онов
    0.46
    }}}\
    0.45
    цима
    0.44
    Geometric
    0.44
    Dreams
    0.44
    நு
    0.44
    POSITIVE LOGITS
     admi
    0.52
     subjug
    0.49
     permiss
    0.48
     G
    0.48
     these
    0.48
     g
    0.47
     exoner
    0.47
     These
    0.46
    ppled
    0.46
     disipl
    0.46
    Activations Density 0.007%

    No Known Activations