© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34930
    Prev
    Next
    INDEX
    Explanations

    sender, received, names, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    Standardization, iOS, leisure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     menjalani
    0.50
     cmake
    0.49
    -
    0.48
     trimestre
    0.48
     coef
    0.48
     bodice
    0.47
     russe
    0.46
     PDK
    0.46
    ᱔
    0.46
     سازی
    0.46
    POSITIVE LOGITS
    ValueError
    0.51
    Kumar
    0.46
    Sender
    0.46
    Ellis
    0.45
    last
    0.45
    кової
    0.42
    Diversity
    0.42
    aszt
    0.42
    sender
    0.41
    received
    0.41
    Activations Density 0.000%

    No Known Activations