© 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. 34-GEMMASCOPE-RES-131K
    7. 59435
    Prev
    Next
    INDEX
    Explanations

    getting or setting properties

    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_34/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
     doigt
    -1.08
     alip
    -1.07
     mercen
    -1.07
     maillot
    -1.06
     oeil
    -1.04
     sement
    -1.04
     summari
    -1.02
     kalori
    -1.02
     kaos
    -1.02
     miroir
    -1.02
    POSITIVE LOGITS
     can
    1.53
     name
    1.39
     supported
    1.33
     get
    1.27
     required
    1.22
     applicable
    1.22
     should
    1.17
     supports
    1.16
     support
    1.13
     Name
    1.13
    Activations Density 0.021%

    No Known Activations