© 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. 19
    Prev
    Next
    INDEX
    Explanations

    the or phrases starting with the

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

    ranging from X to Y

    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
    ות
    0.26
    i
    0.26
    ませんが
    0.26
    ﭑ
    0.25
    ৯
    0.25
    可谓
    0.24
    茆
    0.23
    ర్
    0.23
    唛
    0.23
    纍
    0.23
    POSITIVE LOGITS
     the
    0.34
     a
    0.33
     to
    0.30
     an
    0.30
     behalf
    0.29
     you
    0.28
     be
    0.27
     this
    0.26
     accordance
    0.25
     lawyers
    0.25
    Activations Density 0.363%

    No Known Activations