© 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. 134461
    Prev
    Next
    INDEX
    Explanations

    present followed by research context

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

    present/current state or topic

    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
    ä
    0.64
    在
    0.63
     bằng
    0.61
    各类
    0.60
    .=
    0.60
     అక్కడ
    0.59
     Bücher
    0.58
     estén
    0.58
     különböző
    0.58
     controlado
    0.58
    POSITIVE LOGITS
     edition
    0.60
    Agreement
    0.53
     predicament
    0.52
    FOUND
    0.52
    iment
    0.51
    present
    0.49
    ই
    0.49
    IER
    0.48
    Culture
    0.48
    VERNMENT
    0.48
    Activations Density 0.020%

    No Known Activations