© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1387
    Prev
    Next
    INDEX
    Explanations

    break down

    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_16k_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
     मैंने
    0.38
     অবলম্ব
    0.35
    などを
    0.35
     студен
    0.34
     paesi
    0.33
    }=-\
    0.33
     나는
    0.33
    একটা
    0.32
     acknowledge
    0.31
     강
    0.31
    POSITIVE LOGITS
     this
    0.74
    this
    0.63
     этой
    0.61
     هذا
    0.59
     этого
    0.57
     dieser
    0.57
    この
    0.57
    This
    0.55
     этом
    0.55
     why
    0.55
    Activations Density 0.338%

    No Known Activations