© 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. 150480
    Prev
    Next
    INDEX
    Explanations

    company contact

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

    While technically

    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
    Templates
    0.45
     artificielle
    0.42
    세
    0.42
    ዎቹ
    0.41
     كانوا
    0.41
    崧
    0.41
    Training
    0.40
    णात
    0.40
    らは
    0.40
    كذا
    0.40
    POSITIVE LOGITS
     balsamic
    0.44
     rejuven
    0.42
     Hm
    0.41
    लियों
    0.40
    lovely
    0.40
    mehndi
    0.40
     hm
    0.39
     বহুদিন
    0.39
     粉
    0.39
    おしゃれ
    0.39
    Activations Density 0.000%

    No Known Activations