© 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. 78813
    Prev
    Next
    INDEX
    Explanations

    biblical figures and possessions

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

    conditional outcomes or exceptions

    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
     Excluding
    0.47
     môn
    0.46
     vòng
    0.46
     zespo
    0.43
    崦
    0.42
    шымта
    0.42
     nghiên
    0.41
     lương
    0.41
     delt
    0.40
    兩
    0.40
    POSITIVE LOGITS
    תי
    0.52
    naam
    0.50
    ks
    0.49
    botao
    0.48
    bbb
    0.48
    ऊ
    0.48
    ְ
    0.48
    ťou
    0.47
    wohl
    0.47
    şi
    0.47
    Activations Density 0.001%

    No Known Activations