© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26037
    Prev
    Next
    INDEX
    Explanations

    product identifiers and updates

    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
     their
    -2.03
     some
    -1.69
     more
    -1.63
     people
    -1.61
     other
    -1.55
     those
    -1.51
     came
    -1.45
     three
    -1.42
     every
    -1.41
     only
    -1.39
    POSITIVE LOGITS
     parteci
    1.37
     getAge
    1.28
    ctically
    1.27
     murieron
    1.27
    küche
    1.27
     dizaines
    1.27
     probablement
    1.26
    ۾
    1.26
    unków
    1.24
     detenidos
    1.23
    Activations Density 0.002%

    No Known Activations