© 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. 73222
    Prev
    Next
    INDEX
    Explanations

    account closing, finds water, Bluetooth menu

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

    description of quality or state

    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
     понятия
    0.59
    丂
    0.52
     шпански
    0.50
    اريخ
    0.48
     diagonalization
    0.47
     sequência
    0.46
    現在は
    0.46
     нен
    0.46
    ίλ
    0.46
     неде
    0.46
    POSITIVE LOGITS
    in
    0.55
    lo
    0.54
    ida
    0.54
     Brows
    0.53
    ()=>{
    0.51
    al
    0.51
    ull
    0.51
    LinkedList
    0.51
    ir
    0.50
    if
    0.50
    Activations Density 0.000%

    No Known Activations