© 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. 138371
    Prev
    Next
    INDEX
    Explanations

    located in the solar plexus

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

    structured lists with numbers

    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
     dementia
    0.52
    만
    0.51
    ва
    0.50
     pediatric
    0.50
     skip
    0.49
     skipping
    0.49
     rustic
    0.49
     residual
    0.47
     twice
    0.47
     autism
    0.47
    POSITIVE LOGITS
    nere
    0.45
    ពួកគេ
    0.44
     shēng
    0.43
    ijn
    0.42
     gespe
    0.42
     PARTY
    0.42
    elij
    0.41
    ۔
    0.41
    พวกเขา
    0.41
    rashed
    0.40
    Activations Density 0.001%

    No Known Activations