© 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-65K
    7. 63579
    Prev
    Next
    INDEX
    Explanations

    when a

    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_65k_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
    कोल
    0.51
     mencionados
    0.49
     தொடர்பு
    0.49
    டி
    0.48
    มห
    0.44
     mencionado
    0.44
     컬
    0.43
    whereas
    0.43
     операции
    0.43
    🎭
    0.43
    POSITIVE LOGITS
     with
    0.44
     stretched
    0.44
    An
    0.42
     Bert
    0.41
     (
    0.41
    当时
    0.41
     Reconstruction
    0.39
     flora
    0.39
     comfortable
    0.38
     Accounting
    0.38
    Activations Density 0.003%

    No Known Activations