© 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. 182802
    Prev
    Next
    INDEX
    Explanations

    objects and reservation

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

    disrupts others

    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
     FTSE
    0.50
    茏
    0.46
     పే
    0.44
     Ribe
    0.44
     కొ
    0.43
     giám
    0.43
    礻
    0.43
     Hölder
    0.41
     Dyke
    0.40
     insolvent
    0.39
    POSITIVE LOGITS
    ্যান
    0.48
    ွ
    0.47
    ))*(
    0.46
     зону
    0.46
    なので
    0.45
    굳
    0.45
    ע
    0.45
    だから
    0.44
    trashButton
    0.44
    vascular
    0.44
    Activations Density 0.000%

    No Known Activations