© 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. 96787
    Prev
    Next
    INDEX
    Explanations

    stabbed her

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

    discovering or exploring

    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
    2
    0.60
    conference
    0.48
    1
    0.47
     receptors
    0.46
    toCharArray
    0.46
    bracelet
    0.46
    commod
    0.46
    force
    0.45
    five
    0.45
    setUp
    0.45
    POSITIVE LOGITS
     nový
    0.46
     nemá
    0.45
    衞
    0.45
    啐
    0.45
    АР
    0.45
    ุทธ
    0.44
     можуть
    0.44
     země
    0.44
    clusions
    0.43
    劇場
    0.43
    Activations Density 0.000%

    No Known Activations