© 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. 26158
    Prev
    Next
    INDEX
    Explanations

    names followed by past events

    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
    ⾥
    -1.30
     môžu
    -1.29
     kemarin
    -1.28
    €“
    -1.27
     thier
    -1.27
     telah
    -1.24
     majú
    -1.20
     autrefois
    -1.20
    pueden
    -1.20
    已经
    -1.19
    POSITIVE LOGITS
     was
    2.33
     later
    2.06
     also
    1.89
     became
    1.67
     thereafter
    1.66
     eventually
    1.62
     then
    1.61
     never
    1.49
     remained
    1.44
     continued
    1.39
    Activations Density 0.066%

    No Known Activations