© 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. 47730
    Prev
    Next
    INDEX
    Explanations

    eth and REM cycles

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

    data dependency and subjective reality

    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
    `<
    0.49
    ตรี
    0.45
    वाले
    0.45
    ՜
    0.45
    ੦
    0.44
    上品
    0.44
     ©️
    0.44
     núcleos
    0.43
    孩子们
    0.43
    젊
    0.43
    POSITIVE LOGITS
    kaj
    0.47
    Supported
    0.45
    बम
    0.45
     compensates
    0.44
    '},
    0.44
    beren
    0.44
     PTSD
    0.44
     Salman
    0.43
    '}
    0.43
     पर्सन
    0.43
    Activations Density 0.000%

    No Known Activations