© 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. 27342
    Prev
    Next
    INDEX
    Explanations

    Wild Rose

    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
    text
    -1.08
    typically
    -1.06
     dreadful
    -1.04
     DialogResult
    -1.04
    ]=>
    -1.02
    usually
    -1.00
    و
    -1.00
     ihre
    -0.98
    nes
    -0.97
    ключи
    -0.97
    POSITIVE LOGITS
     still
    1.16
     when
    1.13
    Gentile
    1.10
     this
    1.00
     aliviar
    0.99
    Gön
    0.99
     with
    0.98
     votar
    0.98
    Engl
    0.97
     celebrado
    0.96
    Activations Density 0.000%

    No Known Activations