© 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. 200694
    Prev
    Next
    INDEX
    Explanations

    common phrases

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

    can be, could be, done thoroughly

    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
    빅
    0.50
     빅
    0.45
    ทรัพย์
    0.45
    ⚠️
    0.44
    δρο
    0.43
    in
    0.41
    精准
    0.41
    가
    0.40
    ្សា
    0.40
    峰
    0.40
    POSITIVE LOGITS
     sev
    0.51
     frug
    0.48
    kum
    0.48
     arrogance
    0.48
     incompetence
    0.48
     orders
    0.47
     ott
    0.47
     socialism
    0.47
    kule
    0.47
     jez
    0.46
    Activations Density 0.000%

    No Known Activations