© 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. 17148
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "this is"

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

    this is a/the

    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
    ក៏
    0.39
    degree
    0.38
     bestem
    0.38
    TargetPath
    0.38
    壬
    0.37
    ð
    0.37
    暑
    0.37
    思
    0.36
    นี
    0.36
     largos
    0.36
    POSITIVE LOGITS
     NOT
    0.50
    𝓐
    0.49
     പുതിയ
    0.45
     ಸಮಯ
    0.45
    .):
    0.44
    వలం
    0.43
    rement
    0.43
     पूछता
    0.42
     不是
    0.42
     Everybody
    0.41
    Activations Density 0.112%

    No Known Activations