© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 53247
    Prev
    Next
    INDEX
    Explanations

    starting words in phrases

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

    website, Instagram, motor

    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
     تحديد
    0.41
    객
    0.40
     vaccinations
    0.40
    长时间
    0.39
     schlim
    0.39
    ತೆಯ
    0.38
     deficiencies
    0.38
    csc
    0.37
     трудно
    0.37
     cab
    0.36
    POSITIVE LOGITS
     زن
    0.48
     Notably
    0.45
     教え
    0.44
     सत्ता
    0.43
    !
    0.42
    েক
    0.41
    plotting
    0.41
    Glowing
    0.41
     katta
    0.41
    incing
    0.41
    Activations Density 0.000%

    No Known Activations