© 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. 20871
    Prev
    Next
    INDEX
    Explanations

    defining quantities using "which is"

    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
     Banana
    0.48
    상을
    0.44
     अर्थात
    0.41
    锉
    0.40
     Atau
    0.40
     resides
    0.39
    자를
    0.38
    苣
    0.38
     رہا
    0.38
     banana
    0.37
    POSITIVE LOGITS
    週期
    0.44
     recount
    0.42
    回収
    0.41
    ſſ
    0.41
     weekly
    0.41
    RECTION
    0.41
    ಞ
    0.40
     غز
    0.40
     ጋ
    0.40
    侕
    0.40
    Activations Density 0.001%

    No Known Activations