© 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. 156794
    Prev
    Next
    INDEX
    Explanations

    words following punctuation or abbreviations

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

    common or uncommon

    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
     gathering
    0.50
     at
    0.50
     instit
    0.49
     auditing
    0.49
    公
    0.49
     characterizing
    0.48
     pilgrimage
    0.48
    裁
    0.48
     institutions
    0.47
     exploring
    0.47
    POSITIVE LOGITS
     जवान
    0.54
    kowski
    0.54
    deckung
    0.52
    }}}=
    0.50
    шення
    0.49
     специалисты
    0.49
    PatientR
    0.47
     นึง
    0.47
     ಎಲ್ಲಾ
    0.47
     своему
    0.47
    Activations Density 0.001%

    No Known Activations