© 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. 33496
    Prev
    Next
    INDEX
    Explanations

    code and documentation elements

    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
    และ
    -1.30
    
    -1.30
    および
    -1.23
    ～！
    -1.18
     parachoque
    -1.17
     vinyle
    -1.16
    <tfoot>
    -1.13
    TypeArgs
    -1.11
     Eğ
    -1.11
    もあって
    -1.09
    POSITIVE LOGITS
     \
    1.20
    様な
    1.15
     l
    1.11
    A
    1.08
     persönliche
    1.05
    It
    1.05
    )
    1.05
    S
    1.05
    ことも
    1.04
     —
    1.03
    Activations Density 0.001%

    No Known Activations