© 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. 4293
    Prev
    Next
    INDEX
    Explanations

    proportionally more

    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
    ala
    0.36
    かった
    0.35
    ঙালি
    0.34
    imantan
    0.34
     nació
    0.33
    צוני
    0.33
     computational
    0.33
    ʿ
    0.31
    improvement
    0.31
    obsc
    0.31
    POSITIVE LOGITS
     더욱
    0.55
    特に
    0.45
    更容易
    0.41
     proportionally
    0.41
     უფრო
    0.40
     proportionately
    0.40
     особенно
    0.39
    更是
    0.39
     πιο
    0.39
     besonders
    0.38
    Activations Density 0.370%

    No Known Activations