© 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. 18301
    Prev
    Next
    INDEX
    Explanations

    other words and encouragement

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

    frequently lost items

    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
     Fighter
    0.47
    er
    0.46
    ről
    0.46
     explot
    0.46
     Explorer
    0.45
    r
    0.45
    hhhh
    0.44
    s
    0.43
     Cricket
    0.43
     Counsel
    0.43
    POSITIVE LOGITS
    嶠
    0.45
     يدل
    0.43
    巫
    0.41
     सकी
    0.39
     авгу
    0.39
    澈
    0.39
    iscal
    0.38
    город
    0.38
    actor
    0.37
     動
    0.37
    Activations Density 0.000%

    No Known Activations