© 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. 42669
    Prev
    Next
    INDEX
    Explanations

    President of

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

    normal and healthy sexuality

    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
    不足
    0.50
     melawan
    0.47
    胫
    0.47
    देशीर
    0.44
    शासित
    0.44
    탓
    0.44
    诣
    0.44
    俑
    0.43
     учащихся
    0.43
    ürich
    0.43
    POSITIVE LOGITS
    stream
    0.48
    FUNCTION
    0.46
    ARMA
    0.45
     மி
    0.45
    aide
    0.43
     ને
    0.43
    selenium
    0.43
     objetivos
    0.42
     空
    0.41
     validate
    0.41
    Activations Density 0.000%

    No Known Activations