© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14131
    Prev
    Next
    INDEX
    Explanations

    blue tooth headsets and cases

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

    specific tokens followed by punctuation

    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_16k_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
    רו
    0.57
    ъл
    0.52
    і
    0.52
    า
    0.50
    не
    0.50
    ול
    0.50
    אל
    0.50
    ני
    0.50
     עם
    0.49
    เน
    0.48
    POSITIVE LOGITS
     pewter
    0.44
     delf
    0.43
     phosphates
    0.43
     thio
    0.42
     valves
    0.41
     microprocessor
    0.40
     hydrocarbon
    0.40
     pellet
    0.40
     phosphoric
    0.40
     valve
    0.40
    Activations Density 0.008%

    No Known Activations