© 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. 212391
    Prev
    Next
    INDEX
    Explanations

    Prior Learning

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

    BTU, separate, potential career

    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
     I
    0.58
    et
    0.54
    k
    0.50
    c
    0.50
     atth
    0.47
     They
    0.47
     et
    0.45
    by
    0.45
     insur
    0.45
     amable
    0.45
    POSITIVE LOGITS
    featuresMatrix
    0.51
    レア
    0.50
    ススメ
    0.49
    🤱
    0.46
    desPort
    0.46
     সেখানে
    0.46
    ᔾ
    0.46
     தொடங்கி
    0.46
     జమ
    0.46
    迋
    0.45
    Activations Density 0.001%

    No Known Activations