© 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. 110410
    Prev
    Next
    INDEX
    Explanations

    adjective + adverb

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

    describing, explaining, or solving

    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
    locked
    0.51
    /√
    0.46
    一方面
    0.46
    f
    0.44
    tyard
    0.44
    nag
    0.44
    logged
    0.43
    ┝
    0.43
     ≤
    0.43
     或者
    0.43
    POSITIVE LOGITS
     atractivo
    0.48
     पढ़ाई
    0.47
     belangrijke
    0.46
     जेटली
    0.45
     importantly
    0.44
     atypical
    0.44
     itinéraires
    0.44
     olympiques
    0.44
     முக்கிய
    0.43
     সন্তান
    0.43
    Activations Density 0.001%

    No Known Activations