© 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. 34-GEMMASCOPE-RES-131K
    7. 107106
    Prev
    Next
    INDEX
    Explanations

    put or add

    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_34/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
    一个小
    -0.84
     eût
    -0.73
     nost
    -0.73
    tyfik
    -0.73
     مراجع
    -0.71
     empfangen
    -0.71
     capitulo
    -0.71
     prevenir
    -0.70
     sleepers
    -0.69
     getters
    -0.69
    POSITIVE LOGITS
    put
    1.23
    Put
    1.09
     PUT
    1.00
    PUT
    0.98
     put
    0.94
     Put
    0.88
    Putin
    0.85
    puta
    0.85
    Jobs
    0.84
     Meno
    0.81
    Activations Density 0.017%

    No Known Activations