© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47823
    Prev
    Next
    INDEX
    Explanations

    creating actions or effects

    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
     S
    0.50
    s
    0.50
     kitchen
    0.49
     g
    0.46
    S
    0.44
     circuitry
    0.43
     princess
    0.42
      
    0.41
     Z
    0.41
    Adjust
    0.41
    POSITIVE LOGITS
     जेव्हा
    0.52
     عندما
    0.48
    功效
    0.47
     quando
    0.46
     Ketika
    0.44
    第一时间
    0.43
     когда
    0.43
     όταν
    0.43
    Ketika
    0.43
    ในการ
    0.42
    Activations Density 0.015%

    No Known Activations