© 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. 204326
    Prev
    Next
    INDEX
    Explanations

    salutations and descriptions

    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
    ribute
    0.45
    參
    0.44
     terrorism
    0.43
    terrorism
    0.41
     একত্রে
    0.41
     triangular
    0.40
    solete
    0.39
     obsolete
    0.39
     კან
    0.39
    基督教
    0.38
    POSITIVE LOGITS
     بندر
    0.40
     URL
    0.38
    📺
    0.36
    Datasets
    0.36
    🌊
    0.36
     personnelle
    0.36
    Boat
    0.36
    客人
    0.35
     Bernardo
    0.35
     Screenshot
    0.35
    Activations Density 0.005%

    No Known Activations