© 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. 106662
    Prev
    Next
    INDEX
    Explanations

    tips and questions

    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
    Citiți
    -0.84
     يه
    -0.80
     teaming
    -0.79
     Matri
    -0.77
     greifen
    -0.74
     boosted
    -0.72
     doubting
    -0.71
    Mutagenicity
    -0.71
    ******/
    -0.71
    !」
    -0.70
    POSITIVE LOGITS
     Tip
    1.03
    Tip
    0.81
    相对
    0.80
     kosmety
    0.80
    singular
    0.76
    nextProps
    0.76
    edict
    0.75
     realiz
    0.75
    gone
    0.75
     Tú
    0.74
    Activations Density 0.006%

    No Known Activations