© 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. 160401
    Prev
    Next
    INDEX
    Explanations

    currently browsing

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

    programmed, configured, invisible

    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
     ㅁ
    0.52
     ongel
    0.52
     aryl
    0.47
     대부분
    0.46
    ᔨ
    0.46
    --’
    0.45
    鐒
    0.45
     uzys
    0.44
     yanlış
    0.44
    comings
    0.43
    POSITIVE LOGITS
    菲
    0.60
    F
    0.59
    us
    0.50
    ubs
    0.48
    P
    0.48
    O
    0.48
    劣
    0.46
    评
    0.46
     sao
    0.45
    lis
    0.45
    Activations Density 0.001%

    No Known Activations