© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2285
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases and slang

    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_40_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
    瑄
    0.46
    📶
    0.46
    Density
    0.46
     licensure
    0.46
     متعلق
    0.44
     idk
    0.44
    💻
    0.43
    🎮
    0.43
    诶
    0.43
    🧠
    0.43
    POSITIVE LOGITS
     envisaged
    0.82
     dodgy
    0.71
     bloke
    0.68
     appalling
    0.67
     rubbish
    0.64
     lads
    0.64
     orientated
    0.60
     envisage
    0.60
     flog
    0.59
     hugely
    0.59
    Activations Density 0.010%

    No Known Activations