© 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. 34-GEMMASCOPE-RES-131K
    7. 65196
    Prev
    Next
    INDEX
    Explanations

    Pr, Pf, P, Pros

    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
     Phones
    -0.81
    zać
    -0.81
    ):=\
    -0.77
     thiện
    -0.76
     look
    -0.71
     erst
    -0.71
     Neal
    -0.70
    ict
    -0.70
     enceinte
    -0.69
    lussen
    -0.69
    POSITIVE LOGITS
     Trial
    0.93
    Trial
    0.86
     plötzlich
    0.83
    ğiniz
    0.81
     publicó
    0.80
    Quiz
    0.78
    𝒞
    0.77
    calli
    0.76
    に入れ
    0.76
    って何
    0.75
    Activations Density 0.012%

    No Known Activations