© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15620
    Prev
    Next
    INDEX
    Explanations

    type(...) outputs

    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_40_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
    enca
    0.39
    的作品
    0.37
     alter
    0.37
    amon
    0.37
    えました
    0.37
     ["
    0.37
     aparat
    0.37
     adolescents
    0.36
     மது
    0.36
     دون
    0.36
    POSITIVE LOGITS
    ...>
    0.59
    class
    0.52
     class
    0.48
     sınıf
    0.45
    .>
    0.42
    >(_
    0.41
    </
    0.41
    BL
    0.41
    iclass
    0.41
    >"
    0.41
    Activations Density 0.004%

    No Known Activations