© 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. 199690
    Prev
    Next
    INDEX
    Explanations

    accrued or, emotional character, cry for

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

    sadness, insurance, beyond

    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
     stesse
    0.52
     nossa
    0.49
    ย
    0.48
     nossos
    0.47
     antérieurs
    0.47
     alguns
    0.47
     nuestra
    0.47
     utilisant
    0.47
    viv
    0.46
    apons
    0.46
    POSITIVE LOGITS
    ו
    0.49
    媲
    0.48
     mesmerizing
    0.44
    csvStream
    0.44
     intimidating
    0.43
     వర
    0.43
     تجاوز
    0.43
    AMINATION
    0.43
     напомина
    0.42
     highlights
    0.42
    Activations Density 0.001%

    No Known Activations