© 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. 31088
    Prev
    Next
    INDEX
    Explanations

    place, geography, land

    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
    ସ
    0.43
    деб
    0.43
    ,/*
    0.43
    δευ
    0.41
     ама
    0.40
    йл
    0.39
     ампли
    0.39
     புரிந்து
    0.39
     Eps
    0.39
    isième
    0.38
    POSITIVE LOGITS
    毯
    0.58
    的地
    0.55
    在地
    0.48
    earth
    0.47
     地
    0.47
    地
    0.46
     territorio
    0.45
     earth
    0.44
    狱
    0.42
     Địa
    0.42
    Activations Density 0.001%

    No Known Activations