© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135565
    Prev
    Next
    INDEX
    Explanations

    Romantic composers

    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_40_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
     einger
    0.46
     оки
    0.45
    
    0.44
    Ion
    0.43
    ന്നെ
    0.42
    PACKAGE
    0.42
    Princess
    0.40
    臣
    0.40
    मूलन
    0.39
    earnings
    0.39
    POSITIVE LOGITS
     Villas
    0.44
     imparted
    0.40
     Butterworth
    0.39
    üğ
    0.38
     disabled
    0.37
     op
    0.36
     Mon
    0.36
     Drop
    0.36
     Share
    0.35
     OPC
    0.35
    Activations Density 0.001%

    No Known Activations