© 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. 175085
    Prev
    Next
    INDEX
    Explanations

    guide, charge, need, excellent, majestic

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

    lists from different 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
     Yo
    0.47
    ankan
    0.47
    agamo
    0.44
     {_
    0.43
     Kill
    0.42
    atok
    0.42
     %
    0.42
    ِي
    0.41
     ship
    0.41
     {
    0.41
    POSITIVE LOGITS
    भारत
    0.56
    Breath
    0.52
    राष्ट्रपति
    0.50
    Buddhist
    0.48
    窦
    0.47
    Questions
    0.47
     thous
    0.46
    რძ
    0.46
    Ⴊ
    0.46
    )`
    0.45
    Activations Density 0.001%

    No Known Activations