© 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. 74780
    Prev
    Next
    INDEX
    Explanations

    looking forward

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

    gift card or certificate

    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
     يرد
    0.51
     arriv
    0.50
     jok
    0.49
    </b>
    0.49
    3
    0.48
     fries
    0.48
     faute
    0.47
     redu
    0.47
     gradu
    0.47
    الة
    0.47
    POSITIVE LOGITS
     Arzneim
    0.53
     Ztg
    0.50
    ".*:
    0.48
     ਜਾਂ
    0.48
    вшихся
    0.47
     محصولات
    0.47
    ocompat
    0.46
    \}$,
    0.46
    ítulos
    0.46
     (^{
    0.46
    Activations Density 0.000%

    No Known Activations