© 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. 34-GEMMASCOPE-RES-131K
    7. 117493
    Prev
    Next
    INDEX
    Explanations

    paper title or abstract

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific paper content with mathematical notation and technical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    dominal
    -0.83
     tafel
    -0.80
     مقاله
    -0.80
    losigkeit
    -0.80
     vrienden
    -0.79
    spricht
    -0.79
    cknow
    -0.78
     interieur
    -0.78
     studenten
    -0.77
    のですね
    -0.76
    POSITIVE LOGITS
     about
    0.96
    !
    0.95
    len
    0.88
    EST
    0.88
    cs
    0.88
     ab
    0.84
     !
    0.83
     Gegenstände
    0.81
     Y
    0.80
    adas
    0.80
    Activations Density 0.011%

    No Known Activations