© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1595
    Prev
    Next
    INDEX
    Explanations

    safety protocols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     numerosas
    2.03
     seves
    2.00
    点で
    1.97
     entrambi
    1.85
    缐
    1.83
     nombreux
    1.81
    깁
    1.80
     numerosos
    1.79
    첨
    1.76
     据
    1.75
    POSITIVE LOGITS
     combust
    1.79
     respir
    1.68
     граду
    1.60
     combustion
    1.58
    ˚
    1.58
     listen
    1.57
    Diffuse
    1.52
     ignite
    1.51
    getRandom
    1.50
    req
    1.46
    Activations Density 0.464%

    No Known Activations