© 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. 15-GEMMASCOPE-2-RES-262K
    7. 69972
    Prev
    Next
    INDEX
    Explanations

    explaining potential consequences

    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_15_width_262k_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
    geteilt
    1.26
    黯
    1.25
     naughty
    1.21
     wacky
    1.16
    底下
    1.14
    션을
    1.14
     overworked
    1.13
    に移
    1.13
     divisive
    1.12
     čast
    1.11
    POSITIVE LOGITS
     패턴
    1.81
    尺
    1.72
    registration
    1.70
    checking
    1.67
    DX
    1.66
    holes
    1.64
    ç
    1.62
    ception
    1.62
    Silk
    1.61
     vk
    1.61
    Activations Density 0.000%

    No Known Activations