© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38895
    Prev
    Next
    INDEX
    Explanations

    goal is

    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
    sonaro
    -2.55
     Diese
    -2.39
    ࣭
    -2.36
     overt
    -2.30
    瑧
    -2.28
    </td>
    -2.25
     famosas
    -2.20
     этом
    -2.19
    ندران
    -2.17
     großen
    -2.13
    POSITIVE LOGITS
    </strong>
    2.75
     eletrônico
    2.55
    '
    2.41
    ଝ
    2.39
     atau
    2.27
        
    2.25
     gefe
    2.22
     marinho
    2.20
    的
    2.14
    li
    2.13
    Activations Density 0.015%

    No Known Activations