© 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. 157532
    Prev
    Next
    INDEX
    Explanations

    next measurement

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

    specialized terms and concepts

    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
    一
    0.46
    accoon
    0.45
    olet
    0.44
    صال
    0.43
     länge
    0.42
     tür
    0.42
    örer
    0.40
    iera
    0.40
    iena
    0.40
    اعة
    0.40
    POSITIVE LOGITS
    捻
    0.53
    льных
    0.50
    ウェ
    0.48
     은행
    0.47
    อน
    0.46
     день
    0.45
    ონის
    0.45
     টিম
    0.44
    ("/",
    0.44
     રાશિ
    0.44
    Activations Density 0.001%

    No Known Activations