© 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. 127015
    Prev
    Next
    INDEX
    Explanations

    listing choices or options

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

    insurance or both

    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
     دوسروں
    0.46
    贬
    0.41
     받을
    0.41
     arasındaki
    0.40
     neun
    0.40
     triunfo
    0.38
     അപകട
    0.38
    瑶
    0.38
     zweiten
    0.38
    人都
    0.37
    POSITIVE LOGITS
     both
    0.54
    both
    0.50
    Both
    0.47
     zarówno
    0.46
     दोन्ही
    0.45
    दोनों
    0.43
     BOTH
    0.41
     entrambi
    0.41
     både
    0.40
    前者
    0.40
    Activations Density 0.049%

    No Known Activations