© 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. 31-GEMMASCOPE-2-RES-262K
    7. 93556
    Prev
    Next
    INDEX
    Explanations

    rather than, not replacement

    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
    testimonials
    0.46
    및
    0.45
    ೬
    0.43
     թվ
    0.42
     பாரம்பரிய
    0.41
    ;;
    0.41
    stellungen
    0.40
    …,
    0.40
     pullback
    0.39
     relationships
    0.39
    POSITIVE LOGITS
     Eating
    0.49
     Assay
    0.48
     strictest
    0.47
     interdit
    0.47
     Deed
    0.45
     Tax
    0.45
    嬿
    0.44
    Want
    0.44
     fasted
    0.43
     صحيح
    0.43
    Activations Density 0.005%

    No Known Activations