© 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. 110225
    Prev
    Next
    INDEX
    Explanations

    collapse, airlines, primarily

    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
    ке
    0.48
    ш
    0.47
    za
    0.44
     questioned
    0.44
    gende
    0.43
    га
    0.42
    за
    0.41
     कड़ी
    0.41
    
    0.41
    année
    0.41
    POSITIVE LOGITS
     elevations
    0.47
     ligaments
    0.45
     Morphology
    0.44
     antaranya
    0.44
     由于
    0.43
     प्रवास
    0.42
    𝘼
    0.42
     cathodes
    0.42
     grooves
    0.42
     見
    0.42
    Activations Density 0.004%

    No Known Activations