© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37979
    Prev
    Next
    INDEX
    Explanations

    making growth perform

    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
     fungal
    0.45
    μένων
    0.44
     Branson
    0.43
     doomed
    0.43
    ர்வு
    0.42
     dunia
    0.42
     caveats
    0.42
    忧
    0.42
     அறிவி
    0.41
     गंभीर
    0.40
    POSITIVE LOGITS
     regulate
    0.50
     regulates
    0.47
    으로서
    0.46
     Aynı
    0.45
    することで
    0.44
     помогает
    0.43
     নিরপেক্ষ
    0.43
    তরাং
    0.43
     تساعد
    0.43
     continue
    0.43
    Activations Density 0.003%

    No Known Activations