© 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. 222378
    Prev
    Next
    INDEX
    Explanations

    legal, medical, or technical requirements

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

    parentheticals after certain words

    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
    로운
    0.53
    explos
    0.51
    는
    0.50
    フ
    0.49
    אם
    0.48
    amo
    0.48
    phy
    0.47
     אבל
    0.47
    ‌های
    0.46
    {-\
    0.46
    POSITIVE LOGITS
     Unity
    0.49
     KSI
    0.48
     trillion
    0.47
     taus
    0.47
     rl
    0.47
     Telugu
    0.46
     सीआर
    0.46
     CRI
    0.46
     म
    0.45
     mpl
    0.45
    Activations Density 0.000%

    No Known Activations