© 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. 10-GEMMASCOPE-RES-131K
    7. 71525
    Prev
    Next
    INDEX
    Explanations

    programming code, method calls

    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
     This
    -3.05
    ኧ
    -2.81
    ]
    -2.77
     If
    -2.56
     снимки
    -2.30
     '\
    -2.23
    
    -2.23
    ſſen
    -2.22
     name
    -2.17
    
    -2.17
    POSITIVE LOGITS
    ,…
    2.28
    她
    2.17
    </em>
    2.13
    .",
    2.13
    媃
    2.11
    ent
    2.08
    …(
    2.08
     weitgehend
    2.06
    ان
    2.05
     необходи
    2.05
    Activations Density 0.001%

    No Known Activations