© 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. 74415
    Prev
    Next
    INDEX
    Explanations

    people and others

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

    people say when

    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
     veldig
    0.59
     очень
    0.58
     foarte
    0.54
     (!)
    0.54
     जबरदस्त
    0.54
     ;-)
    0.52
     väldigt
    0.52
     :-)
    0.50
     довольно
    0.50
     VERY
    0.50
    POSITIVE LOGITS
    那我
    0.46
    我不
    0.46
    当我
    0.45
     আমায়
    0.45
     emptiness
    0.43
     istiyorum
    0.43
    жность
    0.43
     predefined
    0.42
    CapsLock
    0.42
    让我
    0.42
    Activations Density 0.105%

    No Known Activations