© 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. 106022
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    explaining terror and fears

    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
    ers
    0.48
    ckers
    0.47
    ával
    0.46
    3
    0.43
    arlier
    0.43
    ERS
    0.42
     miners
    0.42
    gesch
    0.41
     edges
    0.41
    erv
    0.41
    POSITIVE LOGITS
     dibanding
    0.62
     предусматри
    0.58
     その
    0.54
     funcionamento
    0.54
     peningkatan
    0.53
    無料
    0.53
    내는
    0.53
    𒆷
    0.52
     treinamento
    0.52
     praticamente
    0.52
    Activations Density 0.000%

    No Known Activations