© 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. 65264
    Prev
    Next
    INDEX
    Explanations

    purpose of documentation

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

    understand prompts in various languages

    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
    HEN
    0.54
    溧
    0.54
    าด
    0.53
    巳
    0.52
    টে
    0.51
    𝘖
    0.50
    但是在
    0.50
    鬥
    0.49
    لقة
    0.48
    付款
    0.48
    POSITIVE LOGITS
     an
    0.56
     secreted
    0.50
     defined
    0.49
     alias
    0.48
     material
    0.47
     closed
    0.47
     well
    0.46
     felt
    0.46
     beam
    0.46
     axes
    0.46
    Activations Density 0.000%

    No Known Activations