© 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. 61511
    Prev
    Next
    INDEX
    Explanations

    subpoena, flooded, cell, Clinton

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

    assembly language code

    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
    ilitary
    0.50
     દરેક
    0.46
    ixes
    0.45
    c
    0.45
    ন
    0.44
    ac
    0.44
     हिंदुस्तान
    0.44
     عَل
    0.43
    ix
    0.43
     एक्सपीरियंस
    0.43
    POSITIVE LOGITS
    ่ว
    0.44
     insomnia
    0.43
    ర్టు
    0.42
     vibrant
    0.41
     sexually
    0.41
    ሚያ
    0.41
     Sedona
    0.40
     Arthritis
    0.40
     Module
    0.40
    灑
    0.39
    Activations Density 0.000%

    No Known Activations