© 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. 10-GEMMASCOPE-RES-131K
    7. 73935
    Prev
    Next
    INDEX
    Explanations

    on the

    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
    ]=$
    -1.38
    SIZES
    -1.34
    ífica
    -1.31
    needed
    -1.30
    necessary
    -1.26
     eſſ
    -1.25
     signes
    -1.23
    isit
    -1.21
    salms
    -1.20
    ̍t
    -1.18
    POSITIVE LOGITS
     of
    1.89
     other
    1.78
     the
    1.66
     diğer
    1.59
     to
    1.57
     as
    1.54
     innych
    1.49
     them
    1.45
    arangay
    1.45
     aislada
    1.43
    Activations Density 0.078%

    No Known Activations