© 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. 208931
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

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

    Apple logo

    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
    bi
    0.64
    ge
    0.62
    da
    0.59
    vi
    0.57
    gi
    0.57
    c
    0.55
    t
    0.55
    be
    0.55
    di
    0.55
    set
    0.54
    POSITIVE LOGITS
     clavier
    0.58
     vykon
    0.53
     الطريقه
    0.51
     doprav
    0.49
    تباينه
    0.48
    ického
    0.47
     отца
    0.47
     rač
    0.45
     pretože
    0.45
     escritório
    0.44
    Activations Density 0.002%

    No Known Activations