© 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. 38309
    Prev
    Next
    INDEX
    Explanations

    fats and acids

    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
    cosec
    0.51
    eing
    0.51
    ż
    0.50
    ه
    0.50
    ciamo
    0.49
     Avoiding
    0.49
    ၀
    0.49
    ۰
    0.49
    czech
    0.48
    𝟬
    0.48
    POSITIVE LOGITS
     kanker
    0.48
    PO
    0.44
    AUTO
    0.43
    AC
    0.43
    Assembly
    0.42
    ές
    0.42
    Casino
    0.41
    Death
    0.41
    Drug
    0.40
    SuppressWarnings
    0.40
    Activations Density 0.004%

    No Known Activations