© 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. 97085
    Prev
    Next
    INDEX
    Explanations

    nozzle Te

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

    start of sentences

    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
    सब
    0.54
    プレート
    0.49
     plate
    0.48
    晹
    0.48
    铜
    0.47
     пли
    0.45
    平板
    0.45
    㛲
    0.45
    ্লিশ
    0.43
    tcpHeader
    0.43
    POSITIVE LOGITS
     COLE
    0.44
    ↵
    0.43
    ..
    0.42
     .
    0.42
    een
    0.40
    acute
    0.39
     الأخرى
    0.39
     گی۔
    0.39
    agg
    0.38
    iles
    0.38
    Activations Density 0.021%

    No Known Activations