© 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. 64525
    Prev
    Next
    INDEX
    Explanations

    cat owners, durable goods, Microsoft, health

    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
     złot
    0.49
     besoin
    0.47
    ₦
    0.46
     buyout
    0.45
     départ
    0.43
     vlá
    0.43
    pInBuffer
    0.43
     bỏ
    0.42
     voglia
    0.42
     ilaç
    0.42
    POSITIVE LOGITS
    r
    0.51
     ]
    0.49
    s
    0.49
    c
    0.48
    f
    0.47
    x
    0.46
    new
    0.45
    ;
    0.44
    ir
    0.44
    ses
    0.44
    Activations Density 0.007%

    No Known Activations