© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11203
    Prev
    Next
    INDEX
    Explanations

    chapters and parts

    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
     pensieri
    -1.31
     each
    -1.29
    =#
    -1.20
     personaggi
    -1.14
    oczes
    -1.14
     Ländern
    -1.13
    itoba
    -1.12
     these
    -1.10
    --->
    -1.09
    ্ড
    -1.08
    POSITIVE LOGITS
     —
    1.30
    :
    1.20
     سایر
    1.13
    ٩
    1.09
    —
    1.06
     (
    1.05
    代謝
    1.04
     contempla
    1.03
     других
    1.03
    Other
    1.03
    Activations Density 0.018%

    No Known Activations