© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 120695
    Prev
    Next
    INDEX
    Explanations

    pride in services or reputation

    np_acts-logits-general · gemini-2.5-flash-lite

    describing features or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     •
    0.52
    :
    0.47
     stabilizing
    0.47
    5
    0.46
     rent
    0.46
     stabilization
    0.45
     rents
    0.45
     criticized
    0.44
     attracted
    0.44
     simmering
    0.43
    POSITIVE LOGITS
     বক্তৃতা
    0.46
    ᕼ
    0.46
     বক্ত
    0.46
    থেকে
    0.45
    嶅
    0.45
     डिप्टी
    0.45
    পর
    0.44
    তাই
    0.44
    Combined
    0.44
     більше
    0.44
    Activations Density 0.000%

    No Known Activations