© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32390
    Prev
    Next
    INDEX
    Explanations

    help people buy

    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
    ել
    0.47
    橄
    0.47
    队友
    0.46
    ﺄ
    0.42
     grounding
    0.42
     ধর্মীয়
    0.40
     旅行
    0.38
    িয়
    0.38
    蕈
    0.38
     unrecognized
    0.38
    POSITIVE LOGITS
     organise
    0.68
     specialises
    0.64
     organising
    0.63
     maximise
    0.63
     specialise
    0.61
     specialising
    0.60
     classed
    0.59
     minimise
    0.58
     optimise
    0.57
     specialised
    0.56
    Activations Density 0.001%

    No Known Activations