© 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. 3840
    Prev
    Next
    INDEX
    Explanations

    on-policy or resistance

    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
    вър
    0.53
    ዝና
    0.52
    vius
    0.49
    ம்பிய
    0.49
    жении
    0.49
    𝚍
    0.49
    摩托
    0.49
    bromo
    0.48
    чу
    0.48
    乆
    0.48
    POSITIVE LOGITS
     Washington
    0.64
     WASHINGTON
    0.57
    Washington
    0.53
     stressors
    0.53
    </b>
    0.51
     promote
    0.49
     donors
    0.49
     Promote
    0.49
     stressing
    0.49
    </u>
    0.48
    Activations Density 0.007%

    No Known Activations