© 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. 31422
    Prev
    Next
    INDEX
    Explanations

    file references

    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
    ֫
    -0.79
    AGED
    -0.72
     tergantung
    -0.72
    сомо
    -0.71
    почка
    -0.71
     imagenes
    -0.70
    EXECUTIVE
    -0.70
    İY
    -0.69
    ssystem
    -0.69
    Armstrong
    -0.69
    POSITIVE LOGITS
    знать
    0.74
     Uch
    0.69
     RAM
    0.66
     bridging
    0.65
    袴
    0.64
    Uid
    0.64
    何より
    0.63
    녕
    0.63
     Überblick
    0.63
    brid
    0.61
    Activations Density 0.073%

    No Known Activations