© 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. 72116
    Prev
    Next
    INDEX
    Explanations

    quantity or comparison

    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
    いっ
    -1.39
    に入れ
    -1.36
     acht
    -1.32
    €“
    -1.31
     ทำ
    -1.30
    臜
    -1.29
     direto
    -1.29
     foremost
    -1.27
     dando
    -1.27
     Cette
    -1.25
    POSITIVE LOGITS
     of
    2.09
     people
    1.66
     each
    1.55
     in
    1.38
     بخوانید
    1.31
     than
    1.30
     one
    1.25
     Surprisingly
    1.20
     which
    1.19
     started
    1.19
    Activations Density 0.040%

    No Known Activations