© 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-262K
    7. 54875
    Prev
    Next
    INDEX
    Explanations

    Population Increases, Fit, Animals, law, Core concept

    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_262k_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
     esiste
    0.44
    દા
    0.43
    𝓶
    0.43
    ◌
    0.43
    𝔯
    0.43
    து
    0.42
    ATION
    0.42
     zobac
    0.42
     ಮೋ
    0.42
    𝔦
    0.41
    POSITIVE LOGITS
     Kindergarten
    0.37
     hinten
    0.37
     выру
    0.37
     renormalized
    0.36
     negotiated
    0.35
    indruck
    0.35
     spatially
    0.35
     فس
    0.34
    adillo
    0.34
     furlough
    0.34
    Activations Density 0.001%

    No Known Activations