© 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. 10-GEMMASCOPE-RES-131K
    7. 102856
    Prev
    Next
    INDEX
    Explanations

    location 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_10/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
    {
    -1.53
     grosso
    -1.49
     simpat
    -1.39
     politiker
    -1.39
    pantalones
    -1.38
    ANTAGE
    -1.31
    ﮨ
    -1.30
    technologies
    -1.29
     juſ
    -1.28
     idiota
    -1.28
    POSITIVE LOGITS
    </strong>
    2.05
     also
    1.62
     jesteśmy
    1.55
    </sub>
    1.53
     pleas
    1.46
     jus
    1.38
    âmetro
    1.35
     υπάρχει
    1.34
     especially
    1.30
    孳
    1.30
    Activations Density 0.022%

    No Known Activations