© 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. 19583
    Prev
    Next
    INDEX
    Explanations

    availability and descriptions

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

    phone number verification

    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
     place
    0.53
    ць
    0.50
    e
    0.50
    ारक
    0.49
     hovered
    0.47
     army
    0.45
     réforme
    0.45
     smlou
    0.44
     blockchain
    0.44
     acompan
    0.44
    POSITIVE LOGITS
     കൊണ്ട്
    0.49
    lardan
    0.46
    ynthia
    0.46
     Brothers
    0.46
     %@
    0.44
     Link
    0.44
    lara
    0.43
     Genetics
    0.43
     yüzde
    0.43
     Pittsburg
    0.43
    Activations Density 0.000%

    No Known Activations