© 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. 17228
    Prev
    Next
    INDEX
    Explanations

    voluntary choice and human will

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

    non-consensual acts and exploitation

    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
    נו
    0.54
    มาก
    0.46
    าว
    0.46
    Primitive
    0.46
    प्प
    0.45
    gx
    0.45
    ง
    0.45
    ਾ
    0.44
    Tenemos
    0.44
    าส
    0.43
    POSITIVE LOGITS
     defendants
    0.52
     voluntary
    0.52
     signatories
    0.49
     perpetrator
    0.48
     লিপিবদ্ধ
    0.48
     voluntarios
    0.47
     volunt
    0.46
     motivación
    0.45
     perpetrators
    0.44
     motivator
    0.44
    Activations Density 0.000%

    No Known Activations