© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126447
    Prev
    Next
    INDEX
    Explanations

    data and tables

    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
     prey
    0.50
     propres
    0.49
     quant
    0.48
     communicate
    0.47
     CO
    0.45
    の
    0.44
     hyper
    0.43
     on
    0.43
     hair
    0.43
     communicated
    0.43
    POSITIVE LOGITS
    Loksatta
    0.55
    Correlation
    0.54
    Atlet
    0.52
    Calories
    0.52
    Jahr
    0.52
    Promotion
    0.51
    Ϻ
    0.51
    Conference
    0.50
    Confusion
    0.50
    Qatar
    0.50
    Activations Density 0.006%

    No Known Activations