© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48247
    Prev
    Next
    INDEX
    Explanations

    blob/master/

    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
    }$
    -2.25
    It
    -2.13
    The
    -1.99
     It
    -1.96
    th
    -1.95
    from
    -1.93
    🏞
    -1.86
    This
    -1.84
     इसे
    -1.84
    」、「
    -1.81
    POSITIVE LOGITS
    “
    2.05
     größte
    2.05
    いちご
    1.94
    umbnail
    1.91
    
    1.90
    ついでに
    1.84
    sprzedam
    1.84
    tarte
    1.81
    ᡴ
    1.80
    餮
    1.77
    Activations Density 0.005%

    No Known Activations