© 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. 111955
    Prev
    Next
    INDEX
    Explanations

    . , thinking

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

    can explain or try

    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
    (
    0.51
    http
    0.47
    экономи
    0.43
     необходимо
    0.43
    當然
    0.43
     Needless
    0.40
     {},
    0.40
    بعاد
    0.40
    числения
    0.39
     떠
    0.39
    POSITIVE LOGITS
     immunost
    0.51
     vimos
    0.46
     एंटी
    0.44
     immunoprec
    0.43
     veterin
    0.43
     ভাঙ্গা
    0.41
    缇
    0.40
     hemos
    0.40
     seleccione
    0.40
     infar
    0.38
    Activations Density 0.002%

    No Known Activations