© 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. 60969
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    "And" followed by "you" or "I"

    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
    ூ
    0.52
    衛
    0.51
    x
    0.45
    ка
    0.44
     マ
    0.44
    на
    0.43
    [++
    0.43
    dif
    0.42
    デイ
    0.42
    ли
    0.42
    POSITIVE LOGITS
     authoritarian
    0.52
    ట్ల
    0.49
     khăn
    0.48
     सुनी
    0.47
     चर्चा
    0.47
     RCMP
    0.47
     पढ़ी
    0.46
    攢
    0.46
     учены
    0.46
     jogos
    0.46
    Activations Density 0.000%

    No Known Activations