© 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. 202408
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific continuations

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

    vocal style

    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
     透
    0.46
     BAC
    0.46
     specially
    0.44
     指定
    0.43
     distinction
    0.43
    の位置
    0.43
     kJ
    0.43
     autoimmunity
    0.42
    U
    0.42
     国
    0.41
    POSITIVE LOGITS
    لسل
    0.60
    ا
    0.58
    هم
    0.56
    ال
    0.54
    ر
    0.52
    𝙧
    0.52
    lhe
    0.52
    ধ
    0.52
    다
    0.51
    而
    0.51
    Activations Density 0.005%

    No Known Activations