© 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. 49831
    Prev
    Next
    INDEX
    Explanations

    Review:been seenmonitoring pointbestdelete ALLFury Warriorseldom housebroke

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

    creating attraction

    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
    a
    0.50
    into
    0.50
    in
    0.49
    f
    0.47
    other
    0.46
     Accra
    0.46
     London
    0.46
    b
    0.46
    Sample
    0.45
    business
    0.45
    POSITIVE LOGITS
    ية
    0.49
    神秘
    0.48
    ियाँ
    0.47
    身为
    0.46
    ÍA
    0.46
    نة
    0.45
    衄
    0.45
     hő
    0.44
    赦
    0.44
    ర్శ
    0.44
    Activations Density 0.000%

    No Known Activations