© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    anti-aging compounds

    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
     scholarships
    0.54
     vapeur
    0.52
     doigts
    0.51
     linéaire
    0.50
     ල
    0.50
     ස
    0.49
     ຊ
    0.49
     indispensables
    0.48
     ହ
    0.48
     kaleidoscope
    0.47
    POSITIVE LOGITS
    AM
    0.51
    Effective
    0.49
    t
    0.49
    Access
    0.47
    Illinois
    0.47
    to
    0.45
    Async
    0.45
     Effective
    0.44
    Anti
    0.44
    ва
    0.43
    Activations Density 0.010%

    No Known Activations