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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 76685
    Prev
    Next
    INDEX
    Explanations

    explaining or describing content

    np_acts-logits-general · gemini-2.5-flash-lite

    explanation and illustration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ры
    0.50
     eléctricos
    0.48
     ekstra
    0.46
    礦
    0.46
    टेज
    0.45
    collectibles
    0.44
     capace
    0.44
    ⧐
    0.44
    يكم
    0.44
    icità
    0.44
    POSITIVE LOGITS
    讲述
    0.49
    解説
    0.45
     explic
    0.43
     설명
    0.42
     강조
    0.42
    聞き
    0.41
    I
    0.40
     이해
    0.40
     explain
    0.39
    描写
    0.39
    Activations Density 0.002%

    No Known Activations