© 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. 101472
    Prev
    Next
    INDEX
    Explanations

    She, LinkedIn, concatenation, turning, storytelling

    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
    3
    0.60
    0
    0.58
    D
    0.54
    bs
    0.52
    2
    0.52
    1
    0.51
    os
    0.50
    j
    0.48
    b
    0.47
    P
    0.47
    POSITIVE LOGITS
     价
    0.60
     égales
    0.58
     corz
    0.56
     prioridad
    0.52
     买
    0.52
    酺
    0.52
     każ
    0.50
     专业
    0.50
     camisetas
    0.50
     Estoy
    0.50
    Activations Density 0.005%

    No Known Activations