© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15235
    Prev
    Next
    INDEX
    Explanations

    down, Strain, pipe, line, Br, Morph, attack, Choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    য়াদ
    0.70
     Arora
    0.66
     appliances
    0.65
    Heath
    0.64
     establishments
    0.64
    耆
    0.63
     HVAC
    0.63
     సమీ
    0.62
     IAS
    0.61
    ם
    0.61
    POSITIVE LOGITS
     satunya
    0.92
     suic
    0.89
     फलस्वरूप
    0.86
    をつけて
    0.86
    imetype
    0.81
     حذف
    0.80
    瓒
    0.80
     ambivalent
    0.79
     cárc
    0.79
    克力
    0.79
    Activations Density 0.101%

    No Known Activations