© 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. 46759
    Prev
    Next
    INDEX
    Explanations

    tracking searches

    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
    Anthrop
    0.43
    ᔨ
    0.39
    ått
    0.39
     ausgewählt
    0.38
    🏕
    0.38
     pošt
    0.38
    작가
    0.38
    履行
    0.38
     nødv
    0.38
    ARTER
    0.38
    POSITIVE LOGITS
     –
    0.48
     gracias
    0.45
     histories
    0.45
     reversed
    0.44
    estes
    0.44
     t
    0.43
     --
    0.43
     encountered
    0.43
    et
    0.43
     powered
    0.43
    Activations Density 0.001%

    No Known Activations