© 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. 172626
    Prev
    Next
    INDEX
    Explanations

    actual patent

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

    2

    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
    পান
    0.48
     Zukunft
    0.44
     Naj
    0.44
     Topics
    0.44
     società
    0.43
     kimia
    0.43
    温
    0.42
     ڈھاکہ
    0.42
     conducted
    0.42
     laaj
    0.41
    POSITIVE LOGITS
    𝗵
    0.54
    フェイス
    0.52
    funk
    0.50
     воин
    0.49
    dade
    0.49
    eksi
    0.48
    VIII
    0.47
     може
    0.47
    osaur
    0.46
     فس
    0.46
    Activations Density 0.000%

    No Known Activations