© 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-65K
    7. 39873
    Prev
    Next
    INDEX
    Explanations

    contrasting statements or caveats

    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_65k_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
     mutta
    0.47
     pero
    0.46
    িয়৷
    0.46
    但我
    0.46
     ஆனால்
    0.45
    但是我
    0.45
     Nhưng
    0.45
    ஆனால்
    0.44
     但
    0.44
     actitud
    0.43
    POSITIVE LOGITS
    Equal
    0.43
     außergewöhn
    0.40
    までの
    0.38
    Throws
    0.37
    Conceptual
    0.37
    Dangerous
    0.37
     extraordinary
    0.36
    Chim
    0.36
     novelty
    0.36
     يصبح
    0.36
    Activations Density 0.117%

    No Known Activations