© 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. 143875
    Prev
    Next
    INDEX
    Explanations

    roman citations formatting

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

    question or problem statement

    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
     eBook
    0.45
     ต
    0.43
    }{
    0.42
     parabolic
    0.41
     ऑगस्ट
    0.41
     Webinar
    0.41
     ഈ
    0.40
     Echt
    0.40
     ChatGPT
    0.40
     Dah
    0.39
    POSITIVE LOGITS
    विंद
    0.54
     marido
    0.44
    τερ
    0.41
     cirrhosis
    0.41
    𒊕
    0.40
    不管是
    0.39
    দৌ
    0.39
     estoy
    0.38
    GLAND
    0.38
    iritto
    0.38
    Activations Density 0.002%

    No Known Activations