© 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. 109734
    Prev
    Next
    INDEX
    Explanations

    embodiments, sensors, example

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

    control, graph, list, IP addresses

    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
    )
    0.61
    )،
    0.48
    物の
    0.48
    ের
    0.47
     Surveys
    0.46
    лана
    0.45
     chiesa
    0.45
     francs
    0.45
    )$,
    0.44
    SUN
    0.43
    POSITIVE LOGITS
    ifika
    0.48
    istel
    0.45
     unbearable
    0.44
    éricos
    0.44
     अनिवार
    0.44
    uclease
    0.44
    durationType
    0.44
    iqueness
    0.44
    aksha
    0.44
    andfeel
    0.44
    Activations Density 0.000%

    No Known Activations