© 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. 81064
    Prev
    Next
    INDEX
    Explanations

    directions, locations, or timeframes

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

    historical context or facts

    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
     сопер
    0.49
    хии
    0.49
    𝒓
    0.48
    フランス
    0.46
    [['
    0.45
    ими
    0.44
    мит
    0.44
    ੂ
    0.44
    й
    0.44
    コク
    0.44
    POSITIVE LOGITS
     relat
    0.46
     HAN
    0.46
     That
    0.46
     E
    0.45
     elektri
    0.45
     bari
    0.45
     SB
    0.45
    !
    0.45
     THIS
    0.45
     DH
    0.45
    Activations Density 0.002%

    No Known Activations