© 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. 13384
    Prev
    Next
    INDEX
    Explanations

    preposition followed by article or noun

    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
     whatnot
    -1.15
    也會
    -1.14
    also
    -1.12
    也会
    -1.08
     It
    -1.05
     
    -1.05
     (
    -1.04
    等は
    -1.03
    It
    -1.02
     &
    -1.00
    POSITIVE LOGITS
    GRAFÍA
    1.31
    }}=
    1.30
     }))
    1.23
    俢
    1.22
    BRARY
    1.20
    verifyException
    1.17
     ellos
    1.17
     salonu
    1.16
    ᾽
    1.16
     }));
    1.15
    Activations Density 0.244%

    No Known Activations