© 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. 110273
    Prev
    Next
    INDEX
    Explanations

    marketing slogans

    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
    '*
    0.46
    З
    0.45
    alli
    0.44
    -
    0.44
     foci
    0.43
     наличие
    0.42
    Manipulation
    0.42
    }}(-
    0.41
    ULT
    0.41
     Guyana
    0.41
    POSITIVE LOGITS
     yourself
    0.55
    o
    0.55
    yourself
    0.50
     nuestro
    0.49
     Yourself
    0.47
     nossos
    0.46
     diciendo
    0.45
     Votre
    0.45
     salty
    0.45
    ュ
    0.44
    Activations Density 0.003%

    No Known Activations