© 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. 68612
    Prev
    Next
    INDEX
    Explanations

    HTML template

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

    instructions and definitions

    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
     Renal
    0.52
     Hacer
    0.48
     Hunts
    0.46
    ール
    0.45
     ():
    0.45
     ét
    0.44
     Ét
    0.44
    嵋
    0.43
     اكتب
    0.43
     Insert
    0.42
    POSITIVE LOGITS
    hate
    0.50
     sebagainya
    0.44
    hora
    0.43
     شهد
    0.42
    гова
    0.41
    सुबह
    0.41
    ری
    0.40
    گو
    0.40
    𝗴
    0.40
    ucha
    0.39
    Activations Density 0.000%

    No Known Activations