© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9537
    Prev
    Next
    INDEX
    Explanations

    associated with

    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
     and
    -2.02
     for
    -1.84
    </h2>
    -1.63
    </h1>
    -1.52
     with
    -1.48
    所有的
    -1.41
     was
    -1.41
    ℅
    -1.37
     through
    -1.36
     póster
    -1.36
    POSITIVE LOGITS
     you
    2.63
    玙
    1.56
     latter
    1.43
    itoriale
    1.42
     –
    1.40
    丫头
    1.38
     będziesz
    1.36
    obten
    1.34
            
    1.31
     féminin
    1.31
    Activations Density 0.039%

    No Known Activations