© 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. 221660
    Prev
    Next
    INDEX
    Explanations

    sexual assault cases

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

    like something

    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
    ERT
    0.57
    💶
    0.50
     উভয়
    0.48
    }")]
    0.48
    ARD
    0.47
    ensión
    0.47
     автомобиль
    0.47
     ሽፋን
    0.46
    ্তে
    0.46
    ভেজ
    0.46
    POSITIVE LOGITS
     bhavati
    0.44
     laten
    0.44
    天
    0.43
     lowly
    0.43
     hearted
    0.43
     fint
    0.43
     istot
    0.42
     assent
    0.42
     hins
    0.41
     keing
    0.41
    Activations Density 0.002%

    No Known Activations