© 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. 190463
    Prev
    Next
    INDEX
    Explanations

    geographic or descriptive ranges

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

    ESP (Encapsulating Payload Protocol)

    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
    ↵
    0.44
     ሁሉም
    0.42
     lad
    0.41
     crime
    0.40
     neut
    0.40
    🤛
    0.40
    伤害
    0.39
     dominance
    0.39
    对方
    0.39
    രുത്
    0.38
    POSITIVE LOGITS
    을
    0.52
    kým
    0.50
    는
    0.49
    기를
    0.46
     interessiert
    0.45
    를
    0.45
    usam
    0.44
    ول
    0.43
    adhan
    0.43
    Annual
    0.43
    Activations Density 0.012%

    No Known Activations