© 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. 110633
    Prev
    Next
    INDEX
    Explanations

    spacing, occupancy, early proof

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

    surprising events

    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
    ้
    0.47
     impulso
    0.45
    दक्षि
    0.45
     ইসলামের
    0.44
    Bacteria
    0.44
    Wnd
    0.44
     ?:
    0.43
    inction
    0.43
    inert
    0.43
    WindowClass
    0.43
    POSITIVE LOGITS
    ாகவும்
    0.49
     miniatures
    0.45
    劇場
    0.45
    opathology
    0.42
    থন
    0.42
    㻁
    0.42
    浻
    0.42
    存在的
    0.42
     матри
    0.42
    थी
    0.42
    Activations Density 0.000%

    No Known Activations