© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35074
    Prev
    Next
    INDEX
    Explanations

    how to do something

    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
     comparten
    -1.23
     ayudan
    -1.21
     poseen
    -1.18
     reciben
    -1.16
     admiten
    -1.13
     sufren
    -1.10
     requieren
    -1.09
     necesitan
    -1.05
     necesitaba
    -1.02
     almacenar
    -1.00
    POSITIVE LOGITS
     this
    1.64
    これは
    1.13
     make
    1.13
    这个
    1.12
     tohto
    1.09
    はこの
    1.07
     czerwca
    1.05
    让
    1.04
     هذا
    1.04
     continua
    1.02
    Activations Density 0.060%

    No Known Activations