© 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. 231855
    Prev
    Next
    INDEX
    Explanations

    young woman

    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
    ├──
    0.48
     hatches
    0.48
     然后
    0.46
     ⿻
    0.46
    ванович
    0.45
    Semaphore
    0.44
    Ꭾ
    0.44
     alors
    0.43
     士
    0.43
     প্রজাত
    0.43
    POSITIVE LOGITS
    е
    0.53
    جا
    0.47
     MIP
    0.47
    ед
    0.46
     Shr
    0.46
     Afr
    0.46
    ída
    0.45
    生活中
    0.45
     Com
    0.44
    具
    0.44
    Activations Density 0.000%

    No Known Activations