© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    comparing things using "compared to"

    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
    </b>
    0.40
     \
    0.39
     dieser
    0.38
    0
    0.37
     Dong
    0.37
     galore
    0.36
     Util
    0.35
    util
    0.35
     achievements
    0.35
     R
    0.34
    POSITIVE LOGITS
     здра
    0.40
     الهمزه
    0.40
     ROUILLER
    0.40
     گاڑی
    0.40
     अगदी
    0.40
    బ
    0.40
    бычно
    0.39
    endrá
    0.39
    Unless
    0.39
    деа
    0.39
    Activations Density 0.010%

    No Known Activations