© 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. 30385
    Prev
    Next
    INDEX
    Explanations

    word followed by specific word

    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
     Xiong
    -0.75
    饷
    -0.75
    meida
    -0.73
    bush
    -0.70
     Bayern
    -0.69
    texpr
    -0.69
    yethyl
    -0.69
    THON
    -0.69
    madrid
    -0.68
    ärin
    -0.68
    POSITIVE LOGITS
    عار
    0.78
     seaside
    0.77
    Werde
    0.77
     harap
    0.77
     jugu
    0.77
     originalen
    0.75
     plage
    0.73
     laik
    0.72
    ụp
    0.71
     portugu
    0.71
    Activations Density 0.021%

    No Known Activations