© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82106
    Prev
    Next
    INDEX
    Explanations

    promises, fears, daily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ය
    0.55
     Impression
    0.50
    اؤن
    0.49
     Partnership
    0.46
     Ş
    0.46
     CHRIST
    0.46
    代的
    0.45
     Absence
    0.45
    ਨ
    0.44
    ions
    0.43
    POSITIVE LOGITS
     señ
    0.51
     banjo
    0.50
     vencer
    0.49
     teclado
    0.48
    悲
    0.45
     piano
    0.44
     harmonics
    0.44
     cranberry
    0.44
    i
    0.44
    чу
    0.44
    Activations Density 0.001%

    No Known Activations