© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167964
    Prev
    Next
    INDEX
    Explanations

    I pity, I told

    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_40_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
     broker
    0.45
     brokers
    0.44
     inspired
    0.37
     inspiración
    0.37
     inspir
    0.36
     audits
    0.36
     fabricate
    0.35
    ን
    0.35
    Ely
    0.35
     duż
    0.35
    POSITIVE LOGITS
     आवश्यकता
    0.40
    chequer
    0.40
     Viewed
    0.40
    须
    0.39
     ECC
    0.38
    睢
    0.38
    uchte
    0.38
    <unused743>
    0.37
     concluding
    0.37
     Leser
    0.36
    Activations Density 0.000%

    No Known Activations