© 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. 42852
    Prev
    Next
    INDEX
    Explanations

    places and services

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

    team at, two sizes

    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
    د
    0.57
     obliterated
    0.50
    دق
    0.50
    д
    0.48
     onDestroy
    0.48
    б
    0.47
    ду
    0.47
    ющих
    0.46
    बरी
    0.45
     ragged
    0.45
    POSITIVE LOGITS
    □
    0.52
    Ev
    0.50
    IE
    0.50
    QUESTIONS
    0.49
    本作
    0.48
    EVA
    0.48
    L
    0.48
    OLIS
    0.47
    ROTTLE
    0.47
    FUTURE
    0.47
    Activations Density 0.000%

    No Known Activations