© 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. 242144
    Prev
    Next
    INDEX
    Explanations

    admission to

    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
    larını
    0.56
    locationY
    0.56
    larının
    0.55
    "?:
    0.53
    บบ
    0.52
    பாளையம்
    0.52
     আয়নগুলির
    0.52
     теркәлүсез
    0.51
     파인더
    0.50
    뢨
    0.50
    POSITIVE LOGITS
     Provident
    0.48
    ut
    0.47
    '
    0.46
     \<
    0.45
     Preface
    0.44
     Clothes
    0.44
    j
    0.44
     Adequate
    0.43
     J
    0.43
     Interim
    0.43
    Activations Density 0.000%

    No Known Activations