© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62576
    Prev
    Next
    INDEX
    Explanations

    stars, sun, space, Elon, UBS, takeover

    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
    Reserve
    0.42
     réserve
    0.40
    Listener
    0.39
    reserve
    0.39
     Tuple
    0.38
    Lower
    0.38
     Y
    0.38
     Reserve
    0.38
    ​
    0.38
     attract
    0.37
    POSITIVE LOGITS
     positivas
    0.51
     positivos
    0.46
     كتبت
    0.44
     frutas
    0.43
    cooking
    0.43
     isother
    0.42
    壓
    0.42
     schrift
    0.41
     positivo
    0.41
    素晴らしい
    0.41
    Activations Density 0.002%

    No Known Activations