© 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. 165303
    Prev
    Next
    INDEX
    Explanations

    comprises the, sulfur, March, can add, judges was, it was, comprehensive was

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

    persistent history forcing Business

    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
    ку
    0.49
     трак
    0.46
     Thatcher
    0.46
     UNDER
    0.45
     служи
    0.44
     五
    0.44
     четыре
    0.43
    к
    0.43
    த்தக்க
    0.42
    вки
    0.42
    POSITIVE LOGITS
    View
    0.51
    全國
    0.50
    it
    0.47
     analis
    0.46
     বাংলায়
    0.46
    Prices
    0.45
    Answer
    0.45
    Well
    0.45
    慚
    0.44
     možete
    0.44
    Activations Density 0.003%

    No Known Activations