© 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. 10-GEMMASCOPE-RES-131K
    7. 12971
    Prev
    Next
    INDEX
    Explanations

    web acl, video channel, bot channel

    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
    Ebay
    -1.61
    pullover
    -1.59
    ösen
    -1.45
     humeur
    -1.39
    ⠐
    -1.34
     hails
    -1.31
    filet
    -1.30
     آزمون
    -1.30
     ͡°
    -1.29
     gosh
    -1.28
    POSITIVE LOGITS
    If
    1.80
     or
    1.79
     you
    1.72
     if
    1.50
    oscopic
    1.38
     possible
    1.36
    <strong>
    1.34
     IBOutlet
    1.34
     produrre
    1.32
    After
    1.30
    Activations Density 0.064%

    No Known Activations