© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 160392
    Prev
    Next
    INDEX
    Explanations

    May third put boots year

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

    felony murder

    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
     Relatively
    0.51
     Importantly
    0.47
    ꒱
    0.47
    蝰
    0.47
     செறிவு
    0.45
     Existem
    0.44
     ответы
    0.44
    膚
    0.44
     Перейти
    0.43
    িশালী
    0.43
    POSITIVE LOGITS
    3
    0.54
    ản
    0.50
     crisis
    0.48
     बचने
    0.47
     indirect
    0.46
    4
    0.46
     dilemmas
    0.45
    3
    0.45
    ín
    0.43
     accessories
    0.42
    Activations Density 0.000%

    No Known Activations