© 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. 212667
    Prev
    Next
    INDEX
    Explanations

    miles from organizations

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

    trust atoms

    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
    ៦
    0.50
     betek
    0.46
    だけでなく
    0.46
     иннова
    0.45
    ^{\#
    0.45
    เวอร์
    0.44
     BETTER
    0.44
     মধ্যকার
    0.43
    ATED
    0.43
    ᱙
    0.43
    POSITIVE LOGITS
     I
    0.45
    ਕੇ
    0.45
     हाई
    0.44
    ٹن
    0.43
     ٹرسٹ
    0.41
     BitmapFactory
    0.40
    hre
    0.40
    리로
    0.40
    reverse
    0.39
     instructing
    0.39
    Activations Density 0.000%

    No Known Activations