© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13006
    Prev
    Next
    INDEX
    Explanations

    rest and REST API

    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
    أ
    0.50
    There
    0.50
    .
    0.49
    Rourke
    0.48
    kelig
    0.47
    Negoti
    0.47
    This
    0.46
    ó
    0.46
     विचारों
    0.46
     तौर
    0.45
    POSITIVE LOGITS
     rests
    1.13
     resting
    1.04
     rested
    1.01
     descans
    1.00
     Resting
    0.97
     rest
    0.92
     Rest
    0.92
    rest
    0.88
    resting
    0.86
     REST
    0.84
    Activations Density 0.024%

    No Known Activations