© 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. 212876
    Prev
    Next
    INDEX
    Explanations

    parent who believes

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

    material of, safer around

    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
    l
    0.56
     invál
    0.56
    ários
    0.52
     bisogno
    0.51
     ज़रूरत
    0.49
    ĸ
    0.48
     нужно
    0.48
     verificación
    0.47
    as
    0.46
     testicule
    0.46
    POSITIVE LOGITS
    datasets
    0.49
    ENDER
    0.41
     간
    0.41
     구
    0.40
    រយៈ
    0.40
     가정
    0.40
     directe
    0.40
    רוב
    0.39
     предполагает
    0.39
    Mw
    0.39
    Activations Density 0.000%

    No Known Activations