© 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. 107951
    Prev
    Next
    INDEX
    Explanations

    disagree, carcinization, difference, secure gateway

    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
    cle
    0.49
    2
    0.48
    로
    0.48
    1
    0.47
    fem
    0.44
    game
    0.42
    一些
    0.42
    real
    0.40
    Certainly
    0.40
    lighting
    0.40
    POSITIVE LOGITS
    ↥
    0.55
     olacaktır
    0.54
     kaisi
    0.52
    arket
    0.52
     pasajeros
    0.49
     सर्वि
    0.49
     ⿻
    0.48
     товара
    0.48
    滖
    0.47
     Kaur
    0.46
    Activations Density 0.010%

    No Known Activations