© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129376
    Prev
    Next
    INDEX
    Explanations

    specific times and dates

    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_22/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
     of
    -1.51
     two
    -1.33
     in
    -1.28
    :
    -1.28
     or
    -1.23
     from
    -1.23
     with
    -1.13
     and
    -1.12
     on
    -1.12
    军队
    -1.11
    POSITIVE LOGITS
    liğ
    1.28
    楽しめます
    1.23
    liği
    1.20
     envoyer
    1.18
     écrire
    1.18
     parfois
    1.16
    liğini
    1.15
    already
    1.13
     recev
    1.13
    ıdır
    1.09
    Activations Density 0.007%

    No Known Activations