© 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. 101466
    Prev
    Next
    INDEX
    Explanations

    washing machine

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

    GPU cloud services

    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
     grossesse
    0.51
     afferma
    0.51
     desenvol
    0.48
    ပါ။
    0.47
     diathermy
    0.46
     Namibia
    0.44
     berjumpa
    0.44
    Ᏹ
    0.44
    RE
    0.44
    certified
    0.44
    POSITIVE LOGITS
     বাড়
    0.50
     eros
    0.49
     صلاح
    0.44
    به
    0.44
    itäts
    0.44
     диск
    0.41
     Massimo
    0.41
    amentul
    0.40
     to
    0.40
     e
    0.40
    Activations Density 0.001%

    No Known Activations