© 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-262K
    7. 168993
    Prev
    Next
    INDEX
    Explanations

    funding, decisions, vaccines, surface, functionality

    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
    o
    0.45
    captured
    0.44
    Special
    0.44
    між
    0.42
    mass
    0.41
    пред
    0.41
    continu
    0.41
    研
    0.41
    current
    0.40
    urgent
    0.40
    POSITIVE LOGITS
     ఎలా
    0.53
     Palo
    0.49
    ugeot
    0.46
    нул
    0.46
    বারেই
    0.45
     Chevrolet
    0.45
     Samoa
    0.44
     OSU
    0.44
     bitOp
    0.44
     Asus
    0.44
    Activations Density 0.010%

    No Known Activations