© 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. 40-GEMMASCOPE-2-RES-262K
    7. 32230
    Prev
    Next
    INDEX
    Explanations

    Social Inclusion, employment, committees

    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_40_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
     sensation
    0.44
     sensations
    0.41
    $&$
    0.40
     eig
    0.39
    *%
    0.39
     haue
    0.39
     xxx
    0.39
    ួន
    0.38
     RetValue
    0.38
    ᴬ
    0.38
    POSITIVE LOGITS
     কমিটি
    0.40
     informative
    0.40
     Roche
    0.39
    tp
    0.39
    Roche
    0.38
     रिले
    0.38
    ረጃ
    0.38
    Social
    0.38
     Rest
    0.37
     Social
    0.36
    Activations Density 0.000%

    No Known Activations