© 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. 31-GEMMASCOPE-2-RES-262K
    7. 37347
    Prev
    Next
    INDEX
    Explanations

    toxicity, burns, listener, focused

    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_31_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
     начинается
    0.45
     عام
    0.44
    ９
    0.44
    夏天
    0.42
    在一
    0.40
     развивается
    0.40
     experimentado
    0.40
     अन्
    0.40
     срок
    0.40
     a
    0.39
    POSITIVE LOGITS
    Jy
    0.46
    ቹን
    0.45
    me
    0.44
     Pilgrim
    0.43
    おそらく
    0.43
     Geh
    0.43
    wdriver
    0.42
    dept
    0.42
    cess
    0.42
    jets
    0.42
    Activations Density 0.002%

    No Known Activations