© 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. 231272
    Prev
    Next
    INDEX
    Explanations

    time words followed by 's

    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
     Telling
    0.46
    david
    0.46
     primeras
    0.44
    rightarrow
    0.43
     Armand
    0.43
     ۳
    0.42
     Henn
    0.42
     Ne
    0.42
     října
    0.41
     початку
    0.41
    POSITIVE LOGITS
    ’
    0.58
     constitutes
    0.48
     లో
    0.46
     happens
    0.45
    的网络
    0.45
     isn
    0.44
    ABLE
    0.44
     appears
    0.43
     merupakan
    0.43
     becomes
    0.43
    Activations Density 0.039%

    No Known Activations