© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1380
    Prev
    Next
    INDEX
    Explanations

    small, little, minimal

    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
     बढ़कर
    0.45
     surpasses
    0.44
    超过
    0.43
     तब्
    0.40
    supseteq
    0.39
    高达
    0.39
     vượt
    0.38
    )>=
    0.38
     puissiez
    0.37
    以上的
    0.37
    POSITIVE LOGITS
     small
    1.63
     minimal
    1.61
     smaller
    1.60
     pequeña
    1.59
     pequena
    1.59
     low
    1.58
    small
    1.57
     niewiel
    1.54
     ಕಡಿಮೆ
    1.52
     صغيرة
    1.49
    Activations Density 0.369%

    No Known Activations