© 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. 219132
    Prev
    Next
    INDEX
    Explanations

    profit center

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

    harm yourself

    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
    に従
    0.50
    Nag
    0.49
    슨
    0.48
    驮
    0.47
     கிள
    0.46
    ToDO
    0.46
    멧
    0.46
     анализа
    0.45
     জাতিকে
    0.45
    驭
    0.45
    POSITIVE LOGITS
    ahue
    0.46
     trzy
    0.43
     parede
    0.42
     byproduct
    0.42
     zugleich
    0.42
     reopened
    0.41
    ╕
    0.41
     totaling
    0.40
     mailing
    0.40
     echar
    0.40
    Activations Density 0.006%

    No Known Activations