© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18673
    Prev
    Next
    INDEX
    Explanations

    to followed by action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     முடியும்
    0.47
     گوئیاں
    0.45
     zodat
    0.44
    residuals
    0.43
     вашем
    0.43
     gewährleisten
    0.42
     WebDriverWait
    0.42
    ]}{
    0.41
    ographiques
    0.41
    вера
    0.41
    POSITIVE LOGITS
     be
    0.56
    pping
    0.56
    ika
    0.56
    un
    0.55
    cek
    0.55
    1
    0.54
     denounce
    0.54
     can
    0.54
    car
    0.52
    ffee
    0.52
    Activations Density 0.020%

    No Known Activations