© 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. 128448
    Prev
    Next
    INDEX
    Explanations

    planned for

    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
    </h3>
    -1.73
    ing
    -1.51
    ة
    -1.45
    yoruz
    -1.44
    ✳
    -1.43
     pintados
    -1.42
    近平
    -1.38
    ції
    -1.38
    وضح
    -1.37
    anyeol
    -1.37
    POSITIVE LOGITS
     there
    1.77
     you
    1.58
     unlike
    1.52
    kursi
    1.45
     to
    1.44
     tetapi
    1.36
    6
    1.36
     like
    1.36
    ."
    1.34
    我有
    1.32
    Activations Density 0.081%

    No Known Activations