© 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. 150577
    Prev
    Next
    INDEX
    Explanations

    measurement data, check, completely illegal, properties, countries, chunk, respect, Riding Hood

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

    planning, foresight, hero's choice, perfectionism

    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
     president
    0.52
     kitchen
    0.52
     )
    0.50
     High
    0.49
     owner
    0.48
     high
    0.48
     Pro
    0.47
     Next
    0.47
     Stockton
    0.47
     Gloucester
    0.46
    POSITIVE LOGITS
    Какой
    0.46
    ೂರಿನ
    0.45
    鈣
    0.45
    縝
    0.44
     Chất
    0.43
     엔진
    0.43
     캐릭터
    0.43
    ща
    0.43
    િયાન
    0.43
    Dichloro
    0.42
    Activations Density 0.001%

    No Known Activations