© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 247526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or state

    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
    стьян
    0.50
     सारा
    0.47
    нен
    0.46
     partid
    0.46
     cheio
    0.46
    あ
    0.46
     लोकांनी
    0.45
     обращения
    0.44
     authorization
    0.43
     redhead
    0.43
    POSITIVE LOGITS
    Signal
    0.50
    HAR
    0.50
     Signal
    0.47
    ص
    0.47
    Primary
    0.47
     enthr
    0.47
     Ebene
    0.47
     Uhr
    0.47
    Sleep
    0.46
    IDENTITY
    0.46
    Activations Density 0.001%

    No Known Activations