© 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. 48287
    Prev
    Next
    INDEX
    Explanations

    to pee

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

    cost, error, students, advantage

    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
     nah
    0.52
     נא
    0.51
    形的
    0.47
     produziert
    0.46
    i
    0.46
    iin
    0.46
     Himalayas
    0.46
     森
    0.45
     Luke
    0.45
     Bahrain
    0.44
    POSITIVE LOGITS
    ל
    0.64
     rubrique
    0.58
    ल
    0.50
    ênt
    0.50
    ницы
    0.48
     boutons
    0.48
    थ
    0.48
     बात
    0.47
     musée
    0.45
     moléculas
    0.45
    Activations Density 0.000%

    No Known Activations