© 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. 116795
    Prev
    Next
    INDEX
    Explanations

    diverse languages or specific terms

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

    add edge to graph or code

    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
    Homo
    0.46
     HOMO
    0.46
    mann
    0.46
    مش
    0.46
    ாரு
    0.45
     Homo
    0.45
     सोम
    0.45
    ל
    0.45
     Simpsons
    0.43
    manes
    0.43
    POSITIVE LOGITS
    éth
    0.48
    éna
    0.47
     noviembre
    0.44
     decimals
    0.41
     шта
    0.40
     isotherms
    0.40
     cords
    0.40
    年も
    0.40
    0.40
     zich
    0.40
    Activations Density 0.001%

    No Known Activations