© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16084
    Prev
    Next
    INDEX
    Explanations

    representations, limited, reduction, problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    ಿದರೆ
    0.35
    ómago
    0.32
    僟
    0.32
    就可以了
    0.32
     때는
    0.31
    니까
    0.31
    某些
    0.31
    叓
    0.30
    ?)
    0.30
    ってます
    0.30
    POSITIVE LOGITS
     reimag
    0.50
     overarching
    0.40
     repurposed
    0.39
     tasked
    0.37
     livestream
    0.37
     dystopian
    0.36
     onboarding
    0.35
     metaverse
    0.35
     streetwear
    0.35
     skillset
    0.35
    Activations Density 0.000%

    No Known Activations