© 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. 43969
    Prev
    Next
    INDEX
    Explanations

    still getting useful responses

    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
     in
    -1.86
     but
    -1.45
     to
    -1.39
    in
    -1.38
     more
    -1.37
    able
    -1.27
     this
    -1.24
     either
    -1.19
    of
    -1.19
    is
    -1.17
    POSITIVE LOGITS
     animales
    1.53
    ༷
    1.53
     incroyable
    1.47
     enemigos
    1.46
     hilos
    1.45
     puntu
    1.43
     harina
    1.42
     episodios
    1.41
     televiz
    1.40
     monedas
    1.39
    Activations Density 0.079%

    No Known Activations