© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 9088
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    mselves
    0.35
    rades
    0.35
    )
    0.35
    né
    0.34
    etre
    0.34
    }$.
    0.32
    yin
    0.32
    .
    0.32
    "
    0.32
    ).
    0.31
    POSITIVE LOGITS
    ↵
    0.47
    できるよう
    0.37
    できるように
    0.36
     %>%
    0.34
    ↵↵
    0.33
     //
    0.33
     Ultrasound
    0.33
    加えて
    0.32
    牙
    0.32
    мма
    0.32
    Activations Density 0.020%

    No Known Activations