© 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. 66883
    Prev
    Next
    INDEX
    Explanations

    the following word

    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
     as
    -1.75
     through
    -1.69
     extraordinarily
    -1.68
    riwal
    -1.64
     one
    -1.63
     Despite
    -1.55
     with
    -1.53
    áus
    -1.52
     sizable
    -1.52
     despite
    -1.51
    POSITIVE LOGITS
    0
    2.47
    }
    1.82
    4
    1.65
     sooo
    1.65
    al
    1.64
    7
    1.61
    8
    1.57
    seven
    1.55
     soooo
    1.54
    5
    1.48
    Activations Density 0.095%

    No Known Activations