© 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. 20
    Prev
    Next
    INDEX
    Explanations

    recipe yield

    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
    LOTREntity
    0.38
    الس
    0.36
     граф
    0.35
    高品質
    0.35
    桝
    0.35
     trattano
    0.34
    Ду
    0.33
    𝔀
    0.33
    อะคาเดมี
    0.33
    gmzy
    0.33
    POSITIVE LOGITS
     findings
    0.37
     FTA
    0.36
    findings
    0.35
     }*/
    0.35
     Findings
    0.35
     dynam
    0.34
    ff
    0.33
    4
    0.33
     Lalu
    0.33
     Gita
    0.33
    Activations Density 0.006%

    No Known Activations