© 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. 187735
    Prev
    Next
    INDEX
    Explanations

    proposed settlement agreement

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

    describing things like

    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
     s
    0.46
     showc
    0.43
     बजा
    0.42
     showbiz
    0.42
     jung
    0.42
     Timing
    0.42
    t
    0.42
     Uncertain
    0.41
    0.41
     kaj
    0.41
    POSITIVE LOGITS
    puce
    0.53
    ᱗
    0.52
    WAM
    0.51
    ДЕ
    0.49
    櫛
    0.49
    付ける
    0.48
     ಎರಡು
    0.48
    綺麗
    0.47
     スマート
    0.47
     éstos
    0.47
    Activations Density 0.000%

    No Known Activations