© 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. 126396
    Prev
    Next
    INDEX
    Explanations

    accommodate, save, exclusively, floats

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

    its vs it's

    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
    batt
    0.54
    Chill
    0.52
    тифика
    0.51
    поли
    0.51
    toare
    0.50
    ん
    0.50
    Quit
    0.49
    βο
    0.47
    れ
    0.47
    quit
    0.47
    POSITIVE LOGITS
     第一
    0.48
     maxime
    0.46
    的第一
    0.46
     పొంద
    0.45
    akos
    0.45
     '.</
    0.44
     maximising
    0.44
     եւ
    0.43
     متحده
    0.43
     রয়েছে
    0.42
    Activations Density 0.000%

    No Known Activations