© 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. 217469
    Prev
    Next
    INDEX
    Explanations

    numerical and month names

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

    AI behavior and comparisons

    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
    ᆸ
    0.53
    손
    0.51
    모델
    0.50
    피
    0.50
    出
    0.49
    ܒ
    0.46
     centimetres
    0.46
    분
    0.46
     cours
    0.45
    ወስ
    0.45
    POSITIVE LOGITS
     अगस्त
    0.54
     Galactic
    0.51
     през
    0.46
     बनाम
    0.46
     среде
    0.46
     फरवरी
    0.44
     গ্যা
    0.44
     کلی
    0.44
    april
    0.44
     AppCompat
    0.43
    Activations Density 0.000%

    No Known Activations