© 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. 76873
    Prev
    Next
    INDEX
    Explanations

    follows "for"

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

    explaining functions or conditions

    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
    uelas
    0.49
     uintptr
    0.47
     McDowell
    0.47
    h
    0.46
    ópolis
    0.46
    šek
    0.45
     Unidos
    0.44
    nation
    0.44
    ,|\
    0.44
    phone
    0.44
    POSITIVE LOGITS
     LABORATOR
    0.53
     playful
    0.50
     prerog
    0.46
     extranj
    0.45
    ות
    0.45
     practised
    0.44
     scant
    0.44
     нему
    0.44
     praktische
    0.43
     wiad
    0.43
    Activations Density 0.002%

    No Known Activations