© 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. 84518
    Prev
    Next
    INDEX
    Explanations

    various followed by different items

    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
    ᐠ
    -1.79
    𓁹
    -1.66
     specif
    -1.66
    kologi
    -1.63
    somewhat
    -1.62
    joueurs
    -1.60
    kalender
    -1.59
     trám
    -1.58
     peeps
    -1.58
     eer
    -1.58
    POSITIVE LOGITS
    .
    2.75
     Following
    2.13
     Surprisingly
    2.09
     Another
    2.08
     After
    1.99
     During
    1.98
    Through
    1.96
     Shortly
    1.95
     Though
    1.92
     Ironically
    1.92
    Activations Density 0.027%

    No Known Activations