© 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. 84290
    Prev
    Next
    INDEX
    Explanations

    references to one

    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
     ninjago
    -1.58
     Simult
    -1.48
     funko
    -1.47
     yoda
    -1.45
     ··
    -1.45
     eiffel
    -1.44
     bieber
    -1.41
    waktu
    -1.41
     simpsons
    -1.38
     xenia
    -1.37
    POSITIVE LOGITS
    )}$
    1.89
     they
    1.84
    </strong>
    1.80
    ),
    1.63
    )$.
    1.60
    )}(
    1.57
     они
    1.52
     al
    1.49
    \}$
    1.48
    €™
    1.48
    Activations Density 0.021%

    No Known Activations