© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69034
    Prev
    Next
    INDEX
    Explanations

    maximum extent

    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
     alkoh
    -1.45
     mengapa
    -1.44
     raha
    -1.40
    umbled
    -1.34
     mian
    -1.33
     maaf
    -1.30
    会儿
    -1.27
    呦
    -1.27
     in
    -1.27
     alip
    -1.25
    POSITIVE LOGITS
    钐
    1.79
     takich
    1.71
     extent
    1.60
    xFFFF
    1.52
    șa
    1.49
     entsprechenden
    1.48
     einschließlich
    1.46
    附属
    1.46
    },
    1.45
     gemeinsam
    1.45
    Activations Density 0.013%

    No Known Activations