© 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. 31-GEMMASCOPE-2-RES-262K
    7. 168724
    Prev
    Next
    INDEX
    Explanations

    component suppliers

    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_31_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
     Gebrauch
    0.53
     datth
    0.50
     Herstellung
    0.50
    .}}
    0.50
     reembolso
    0.49
     ಅಭಿಮಾನ
    0.49
     verwenden
    0.49
     bestimm
    0.49
     ござい
    0.49
     absolv
    0.49
    POSITIVE LOGITS
    Easy
    0.47
    文
    0.46
    白
    0.46
    Set
    0.46
    Vol
    0.46
    瓦
    0.46
    为
    0.45
    <?
    0.45
    Track
    0.45
    色彩
    0.45
    Activations Density 0.006%

    No Known Activations