© 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. 13087
    Prev
    Next
    INDEX
    Explanations

    confession and arrest

    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
     vigilance
    0.41
     outages
    0.41
    ደጋ
    0.40
    ایط
    0.40
    が発生
    0.39
    दुर्
    0.39
     unfriendly
    0.38
    )}_
    0.38
     चिंतित
    0.38
     возник
    0.37
    POSITIVE LOGITS
     confessed
    0.84
     arrested
    0.82
     confess
    0.82
     confession
    0.78
     confesses
    0.72
     confessions
    0.71
     confes
    0.70
     गिरफ्तार
    0.69
     convicted
    0.68
     arrest
    0.68
    Activations Density 0.042%

    No Known Activations