© 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-262K
    7. 19950
    Prev
    Next
    INDEX
    Explanations

    code documentation and declarations

    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_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
    emote
    0.45
     reparation
    0.43
     Frobenius
    0.38
    ❊
    0.38
    úp
    0.38
    emente
    0.37
    insertCell
    0.37
     Repar
    0.37
    én
    0.36
    azote
    0.36
    POSITIVE LOGITS
     themed
    0.42
    หาย
    0.39
     children
    0.38
    屉
    0.37
     lunatic
    0.37
     push
    0.36
     raiz
    0.36
     leg
    0.36
    ุล
    0.36
    icheskij
    0.36
    Activations Density 0.002%

    No Known Activations