© 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. 167287
    Prev
    Next
    INDEX
    Explanations

    emojis and conversational phrases

    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
    geqslant
    0.41
    晰
    0.39
     पूर्
    0.38
     والش
    0.38
    ogs
    0.38
    士
    0.37
     cursed
    0.37
     БД
    0.37
    фон
    0.36
     isop
    0.36
    POSITIVE LOGITS
     ύ
    0.44
     Create
    0.43
    芩
    0.42
     Corruption
    0.39
     Protestant
    0.39
     Decentral
    0.39
     Paperback
    0.39
     Transfer
    0.38
    traditional
    0.38
     Basket
    0.38
    Activations Density 0.000%

    No Known Activations