© 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. 154605
    Prev
    Next
    INDEX
    Explanations

    various international terms

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

    skulls staring, fixing bugs

    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
    understanding
    0.44
    ırl
    0.44
     hoher
    0.42
    oxy
    0.41
     изго
    0.40
    的发
    0.40
     (=
    0.40
     dobre
    0.40
    (=
    0.39
     الكلام
    0.39
    POSITIVE LOGITS
     quelconque
    0.44
    ккей
    0.41
    ncies
    0.41
     Lists
    0.41
     اخیر
    0.41
     américains
    0.40
     dirigeants
    0.40
    više
    0.40
    하시면
    0.40
    जारत
    0.40
    Activations Density 0.001%

    No Known Activations