© 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. 46719
    Prev
    Next
    INDEX
    Explanations

    contrasting open and closed models

    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
    ृती
    0.47
    lysninger
    0.46
    ...............
    0.45
    들이
    0.44
    ⵕ
    0.43
    uki
    0.43
    다는
    0.42
    ਟ
    0.42
    훈
    0.42
    τυ
    0.41
    POSITIVE LOGITS
     Precio
    0.48
     Incent
    0.47
     Prospect
    0.47
     Requires
    0.46
     backed
    0.46
     edificios
    0.45
    alang
    0.44
     magnific
    0.44
     مکان
    0.44
     nasceu
    0.44
    Activations Density 0.007%

    No Known Activations