© 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. 132726
    Prev
    Next
    INDEX
    Explanations

    increase, intensify, and describe

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

    avoiding or describing negative states

    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
     of
    0.52
     is
    0.48
     minis
    0.46
     auricul
    0.45
    ies
    0.44
    ദേ
    0.44
    阴
    0.44
     ingredient
    0.44
    قر
    0.43
     ingles
    0.43
    POSITIVE LOGITS
     ಹೆಚ್ಚಿನ
    0.47
     शानदार
    0.46
     తెలిపారు
    0.46
     zwięks
    0.46
     नियंत्रण
    0.45
     વધ
    0.45
     পর্যবেক্ষণ
    0.44
    <unused1064>
    0.44
     చెప్పారు
    0.44
     типи
    0.43
    Activations Density 0.000%

    No Known Activations