© 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. 40296
    Prev
    Next
    INDEX
    Explanations

    CSS flexbox properties

    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
     Himself
    -1.17
    Ꮉ
    -1.10
     kedua
    -1.08
    内心
    -1.07
     profondità
    -1.07
    ),
    -1.06
    nische
    -1.05
    ).
    -1.05
     jost
    -1.05
    rý
    -1.04
    POSITIVE LOGITS
    1.16
    </em>
    1.13
    ကိုးကား
    1.10
    телем
    1.07
     vectores
    1.06
     wonen
    1.02
     chè
    1.01
     poderosa
    1.01
    skjaer
    0.98
    <bos>
    0.97
    Activations Density 0.001%
    No Known Activations