© 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. 133976
    Prev
    Next
    INDEX
    Explanations

    soul and souls

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

    soul, essence, identity

    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
     efectuar
    0.57
     இதய
    0.56
    ቛ
    0.55
     vở
    0.54
    tourism
    0.53
    lable
    0.52
    荭
    0.52
    تين
    0.52
     manglid
    0.52
    ﭥ
    0.51
    POSITIVE LOGITS
     soul
    0.66
            
    0.59
    0.53
     souls
    0.51
    を発
    0.51
     Soul
    0.48
    <0x0D>
    0.45
     soulful
    0.45
    \
    0.44
    Soul
    0.44
    Activations Density 0.009%

    No Known Activations