© 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. 27322
    Prev
    Next
    INDEX
    Explanations

    lists or structured data

    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
    U
    0.62
    er
    0.58
    t
    0.57
    S
    0.55
        
    0.55
    P
    0.54
    Q
    0.53
            
    0.52
             
    0.52
    R
    0.50
    POSITIVE LOGITS
     prépuce
    0.52
     வளாக
    0.48
    äänt
    0.48
     ойношот
    0.48
    हास
    0.48
     车
    0.47
     ఉత్పత్తి
    0.46
     กี่
    0.45
    PropertySheets
    0.44
     ఉన్నారు
    0.44
    Activations Density 0.000%

    No Known Activations