© 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. 73500
    Prev
    Next
    INDEX
    Explanations

    contract, Test, file

    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
     eenige
    -1.59
     péché
    -1.55
    \%,
    -1.55
    +)$
    -1.54
     Vorgang
    -1.52
     hormigón
    -1.51
    旰
    -1.46
    enosis
    -1.45
    -}
    -1.43
     verkau
    -1.43
    POSITIVE LOGITS
     but
    1.81
     with
    1.55
    jelasan
    1.55
     will
    1.51
    jangkau
    1.38
    iyle
    1.36
    cipta
    1.31
    daging
    1.31
     betale
    1.30
     following
    1.27
    Activations Density 0.001%

    No Known Activations