© 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. 66156
    Prev
    Next
    INDEX
    Explanations

    names following punctuation

    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
     for
    -1.45
     each
    -1.38
     all
    -1.34
     some
    -1.34
     there
    -1.18
     everyone
    -1.15
     Mat
    -1.11
     Po
    -1.05
     Some
    -1.03
     every
    -1.02
    POSITIVE LOGITS
     his
    1.26
    rechten
    1.16
     сейчас
    1.16
     myös
    1.10
    现在
    1.10
    Список
    1.09
    Ngoài
    1.08
    kabel
    1.06
     Consulte
    1.05
     chirurgie
    1.04
    Activations Density 0.067%

    No Known Activations