© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14742
    Prev
    Next
    INDEX
    Explanations

    system and service descriptions

    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_16_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
     ñ
    0.51
    burgo
    0.49
    тель
    0.48
    alda
    0.47
     agglomer
    0.46
     twofold
    0.45
    ହା
    0.45
    elabel
    0.45
    oja
    0.43
    ibi
    0.43
    POSITIVE LOGITS
    表達
    0.54
    يا
    0.53
    翼
    0.52
    表达
    0.51
    丝毫
    0.49
    狷
    0.48
     ZA
    0.47
     wewnętr
    0.47
     Twist
    0.46
    ট
    0.46
    Activations Density 0.000%

    No Known Activations