© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8890
    Prev
    Next
    INDEX
    Explanations

    names ending in suffixes

    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_9_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
    า
    0.60
     zeker
    0.58
    pretrained
    0.57
    gger
    0.56
     añadir
    0.56
    dauer
    0.56
    er
    0.56
    ו
    0.55
    ている
    0.55
    <
    0.55
    POSITIVE LOGITS
     στην
    0.70
     interrogated
    0.68
     Jr
    0.68
    ﺔ
    0.64
     ਅਤੇ
    0.63
     Esq
    0.63
     ಮತ್ತು
    0.62
    oglu
    0.60
    selectAll
    0.59
    iyev
    0.59
    Activations Density 0.054%

    No Known Activations