© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194455
    Prev
    Next
    INDEX
    Explanations

    name, ID, hash, or tag

    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
     alamat
    0.51
     ব্যাক্ত
    0.45
    बेल
    0.43
     endereco
    0.43
    诞
    0.43
    cityName
    0.42
     tulis
    0.42
    磺
    0.42
    ນະ
    0.41
     meneg
    0.40
    POSITIVE LOGITS
    Match
    0.45
    Range
    0.44
    Used
    0.43
     used
    0.43
    List
    0.40
    Als
    0.40
     usados
    0.40
     alone
    0.39
    ringe
    0.39
    resolver
    0.39
    Activations Density 0.041%

    No Known Activations