© 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-16K
    7. 12542
    Prev
    Next
    INDEX
    Explanations

    moving into a place or state

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

    into and following phrase

    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_16k_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
     または
    0.84
     と
    0.73
     экране
    0.70
     ו
    0.68
    ৬
    0.67
    ua
    0.66
     より
    0.66
     の
    0.66
     xmlns
    0.65
     を
    0.64
    POSITIVE LOGITS
    a
    1.13
    o
    0.82
    Into
    0.81
    into
    0.78
     oblivion
    0.76
     adulthood
    0.69
    纳
    0.68
    一定的
    0.63
    ش
    0.63
    يع
    0.61
    Activations Density 0.220%

    No Known Activations