© 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. 22-GEMMASCOPE-RES-131K
    7. 65231
    Prev
    Next
    INDEX
    Explanations

    forEach or each loops

    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
     tomando
    -1.85
     realizando
    -1.80
     gelb
    -1.63
     esperando
    -1.58
     enviada
    -1.56
     vorder
    -1.55
    1
    -1.52
    凄い
    -1.51
     destinada
    -1.51
    perhaps
    -1.50
    POSITIVE LOGITS
    龊
    1.94
    𝑎
    1.88
    嗚
    1.78
    袮
    1.77
     estekak
    1.77
     raiſ
    1.77
    ]$
    1.65
    (&:
    1.60
    )]
    1.59
     philosophie
    1.58
    Activations Density 0.002%

    No Known Activations