© 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. 157632
    Prev
    Next
    INDEX
    Explanations

    I knew, then load, with small

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

    International characters and data input

    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
     وام
    0.47
     Pflanzen
    0.45
    fall
    0.45
     ט
    0.45
     وأ
    0.44
     цветы
    0.44
     springtime
    0.44
     نور
    0.43
     春
    0.42
     אחר
    0.42
    POSITIVE LOGITS
    िले
    0.49
    मीर
    0.48
    čkog
    0.46
    ATCH
    0.45
    ходить
    0.45
     로그인
    0.44
     Input
    0.44
    KEN
    0.43
    राबाद
    0.43
    コの
    0.43
    Activations Density 0.001%

    No Known Activations