© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 98609
    Prev
    Next
    INDEX
    Explanations

    financial inclusion, discrimination, sex, peace

    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
     EXO
    0.43
     PAX
    0.42
     AX
    0.42
     these
    0.41
     every
    0.40
    www
    0.40
     www
    0.40
    𒌷
    0.40
     Pantai
    0.38
     VPS
    0.37
    POSITIVE LOGITS
     manifestaciones
    0.38
     pelaku
    0.37
    依頼
    0.36
     Practitioners
    0.34
     ਨੇ
    0.34
     पहचान
    0.34
     স্বীকৃতি
    0.34
     vormen
    0.33
     vooral
    0.33
    អនុ
    0.33
    Activations Density 0.338%

    No Known Activations