© 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. 22460
    Prev
    Next
    INDEX
    Explanations

    weight gain and indulgence

    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
    splitLength
    0.47
     principled
    0.45
    绿色
    0.42
     reform
    0.41
    凛
    0.41
     transparency
    0.41
     revolutionaries
    0.40
     नैतिक
    0.40
     verde
    0.40
     hygienic
    0.40
    POSITIVE LOGITS
     fatten
    0.84
     indulgence
    0.75
     indulgent
    0.74
     indulging
    0.71
    菓子
    0.68
     indul
    0.67
    肥
    0.66
     indulge
    0.61
     chubby
    0.61
     binge
    0.59
    Activations Density 0.115%

    No Known Activations