© 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. 16-GEMMASCOPE-2-RES-262K
    7. 2050
    Prev
    Next
    INDEX
    Explanations

    appropriate manner, attire, conversation, salary, topics, treatment, behavior

    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_16_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
    س
    1.26
     טוב
    1.13
    স
    1.06
    માં
    1.05
    1.04
     অন
    1.00
     ম
    0.96
     גדול
    0.94
     effett
    0.93
     ন
    0.93
    POSITIVE LOGITS
    i
    1.40
    一
    1.37
    p
    1.30
    u
    1.23
    n
    1.22
    at
    1.20
    in
    1.20
    ب
    1.13
    y
    1.04
    j
    1.02
    Activations Density 0.015%

    No Known Activations