© 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. 4028
    Prev
    Next
    INDEX
    Explanations

    deontology and ontology

    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
    ایط
    0.48
    timestep
    0.47
    менение
    0.47
    Б
    0.46
    Vaterpolo
    0.45
    npc
    0.44
    凶
    0.44
    困难
    0.43
     बहस
    0.43
    难度
    0.43
    POSITIVE LOGITS
     ry
    0.55
    ay
    0.55
    ec
    0.53
     co
    0.53
    ac
    0.52
     è
    0.52
     David
    0.50
     islands
    0.50
     Frédéric
    0.50
     PRO
    0.49
    Activations Density 0.013%

    No Known Activations