© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138062
    Prev
    Next
    INDEX
    Explanations

    booking

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

    common words or phrases

    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
    ד
    0.57
     ауто
    0.52
    აძ
    0.52
    არ
    0.50
     იქნება
    0.50
     მნიშვნელ
    0.50
    之后
    0.49
    گے
    0.49
     ამ
    0.48
    슴
    0.48
    POSITIVE LOGITS
     vanlig
    0.46
     vorhand
    0.45
    istered
    0.43
    jän
    0.43
     allotted
    0.42
    Starter
    0.41
    開始
    0.40
    Already
    0.40
     schon
    0.39
    pt
    0.39
    Activations Density 0.001%

    No Known Activations