© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1010
    Prev
    Next
    INDEX
    Explanations

    kinda basically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     היתה
    -1.05
     Incidentally
    -1.05
     skall
    -1.04
    ;-)
    -0.99
    "");
    -0.98
    #
    -0.98
    😘
    -0.97
    Folks
    -0.97
     remuneration
    -0.96
     необходимо
    -0.96
    POSITIVE LOGITS
     kinda
    1.39
     будто
    1.38
     basically
    1.32
     stuff
    1.28
    とか
    1.17
     meistens
    1.16
    mainly
    1.14
     çoğu
    1.13
    Basically
    1.11
     overall
    1.09
    Activations Density 0.013%

    No Known Activations