© 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. 58655
    Prev
    Next
    INDEX
    Explanations

    you followed by verbs

    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
    䊳
    -1.84
     和
    -1.75
     ถ้า
    -1.73
     leur
    -1.70
     если
    -1.66
    安い
    -1.66
     когда
    -1.62
     jika
    -1.61
    給你
    -1.60
    または
    -1.59
    POSITIVE LOGITS
    想过
    1.65
    isti
    1.62
    owaniem
    1.59
     extrêmement
    1.55
     leal
    1.55
    ский
    1.51
    ја
    1.51
    捺
    1.47
    </i>
    1.45
    ющих
    1.45
    Activations Density 0.004%

    No Known Activations