© 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. 121592
    Prev
    Next
    INDEX
    Explanations

    purchaser must, remarkably, castle builds, remember him, succeeded at

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

    strangely compelled, magically reappear

    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
    ता
    0.55
    Let
    0.52
    But
    0.51
    忘れ
    0.49
    You
    0.48
    Like
    0.48
    さ
    0.48
    Here
    0.47
    If
    0.46
    カリ
    0.46
    POSITIVE LOGITS
     Від
    0.50
     ইং
    0.47
     επ
    0.46
     від
    0.46
    يط
    0.46
     superstructure
    0.45
    owego
    0.45
     iż
    0.45
     protruding
    0.44
     Е
    0.44
    Activations Density 0.000%

    No Known Activations