© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27433
    Prev
    Next
    INDEX
    Explanations

    concept, custom, specific, new

    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_22/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
     facultad
    -1.06
    って思
    -0.94
     требует
    -0.94
    álise
    -0.90
    脓
    -0.90
     вони
    -0.89
     nabíz
    -0.88
    췄
    -0.87
     construct
    -0.86
    Kdo
    -0.85
    POSITIVE LOGITS
     or
    1.21
     kn
    1.10
    otonic
    1.09
    ᐕ
    1.06
    quely
    1.02
    腚
    1.02
    繊
    1.00
    ḥ
    1.00
    vertis
    0.99
     mye
    0.99
    Activations Density 0.086%

    No Known Activations