© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86171
    Prev
    Next
    INDEX
    Explanations

    strictness and selectivity

    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
     Some
    -2.08
     Sadly
    -2.02
     Perhaps
    -1.89
     Many
    -1.88
     It
    -1.85
     Numerous
    -1.82
     Those
    -1.77
     There
    -1.77
     Maybe
    -1.76
     If
    -1.74
    POSITIVE LOGITS
    even
    2.31
    and
    2.28
    or
    2.13
    2
    2.13
    as
    2.05
    cisive
    2.02
    but
    1.95
    less
    1.95
    6
    1.95
    ly
    1.94
    Activations Density 0.011%

    No Known Activations