© 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. 104634
    Prev
    Next
    INDEX
    Explanations

    doubler, fair, engines, oscillation

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

    occur without exceptions

    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
    anque
    0.50
     मस
    0.46
    ايا
    0.46
    ⾏
    0.45
    úde
    0.45
    票房
    0.45
    ों
    0.45
     Mỹ
    0.45
     Judiciary
    0.45
     Bandit
    0.45
    POSITIVE LOGITS
     tablette
    0.58
    V
    0.48
     apar
    0.48
     society
    0.47
    C
    0.46
     oscillation
    0.45
     teha
    0.45
     presse
    0.44
     capas
    0.44
     oscill
    0.43
    Activations Density 0.000%

    No Known Activations