© 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. 128221
    Prev
    Next
    INDEX
    Explanations

    new or following common phrases

    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
    である
    -1.20
    省市镇
    -1.01
     konu
    -0.98
     convite
    -0.97
    瞟
    -0.96
     podía
    -0.95
     vivía
    -0.93
    她就
    -0.92
    </b>
    -0.91
     by
    -0.91
    POSITIVE LOGITS
     he
    1.16
     meningkatkan
    1.15
     alcuni
    1.15
    相关文章
    1.10
    𝒟
    1.09
     membuat
    1.08
     esterni
    1.07
     gruppi
    1.06
    せた
    1.06
    ésil
    1.06
    Activations Density 0.000%

    No Known Activations