© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4881
    Prev
    Next
    INDEX
    Explanations

    combination of tokens forming words

    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_29_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
    JKL
    0.83
    popo
    0.83
    ISIS
    0.80
    ccccc
    0.78
    butanol
    0.76
    ENANCE
    0.74
    빡
    0.73
     aaa
    0.73
    িয়ার
    0.73
     AAA
    0.73
    POSITIVE LOGITS
    ى
    0.75
    ை
    0.72
    ן
    0.66
    us
    0.64
    काच्या
    0.63
    eOut
    0.61
     prestataire
    0.59
     Combination
    0.58
    oLocations
    0.58
     Commissions
    0.58
    Activations Density 0.275%

    No Known Activations