© 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. 64822
    Prev
    Next
    INDEX
    Explanations

    as in well

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

    attraction, love, or cheering

    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
    G
    0.47
    Camera
    0.45
    H
    0.43
    Managing
    0.43
    ঙ্গার
    0.43
    IQR
    0.43
    Ű
    0.42
    、
    0.42
    შ
    0.42
    カメラ
    0.42
    POSITIVE LOGITS
     উক্ত
    0.52
     ONLY
    0.47
    hAP
    0.44
     jedynie
    0.41
     ἡ
    0.41
     całkow
    0.41
    टरनेट
    0.40
    ]<<"
    0.39
    没人
    0.39
     somit
    0.39
    Activations Density 0.000%

    No Known Activations