© 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. 220090
    Prev
    Next
    INDEX
    Explanations

    saying what manner

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

    leading to

    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
    ฟ
    0.47
    את
    0.44
    Variant
    0.44
    Stylish
    0.43
    메
    0.43
    골
    0.43
    振り返
    0.43
    한국
    0.42
    ফ
    0.42
    탄
    0.42
    POSITIVE LOGITS
     jóvenes
    0.58
     jovens
    0.58
     fluxes
    0.49
     movimientos
    0.48
     phenytoin
    0.47
     amplitudes
    0.47
     melatonin
    0.46
     disturbances
    0.45
     movements
    0.45
     neurons
    0.45
    Activations Density 0.001%

    No Known Activations