© 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. 22039
    Prev
    Next
    INDEX
    Explanations

    very obvious answer

    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
    Cuáles
    0.48
    Essay
    0.41
    鋆
    0.41
    Malley
    0.40
     दिख
    0.40
    蕖
    0.40
    艾
    0.40
    ҳа
    0.39
    WeatherData
    0.39
    Estoy
    0.39
    POSITIVE LOGITS
    ுற
    0.39
    |-
    0.38
     originates
    0.38
     slechts
    0.38
     nho
    0.38
     cult
    0.38
     &:
    0.37
    natural
    0.37
     numer
    0.36
     compon
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.