© 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. 219
    Prev
    Next
    INDEX
    Explanations

    emphasis or quotes

    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
     abusers
    0.47
    ∞</
    0.47
     ejac
    0.45
     companionship
    0.45
     emptiness
    0.44
     cumul
    0.44
    ުޅ
    0.44
     offend
    0.43
     حصہ
    0.42
     окружа
    0.42
    POSITIVE LOGITS
    7
    0.55
    2
    0.54
    8
    0.52
    4
    0.49
     टेन
    0.47
     powied
    0.47
    known
    0.46
    Power
    0.46
    medizin
    0.46
    explorer
    0.46
    Activations Density 0.001%

    No Known Activations