© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 83948
    Prev
    Next
    INDEX
    Explanations

    specific routes

    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
     understands
    0.42
     njeg
    0.41
     ''
    0.40
     seves
    0.39
     adhere
    0.38
     adheres
    0.38
    РУ
    0.37
    ''_
    0.37
    పో
    0.36
    ahami
    0.36
    POSITIVE LOGITS
     UpdateWindow
    0.46
     காலநிலை
    0.42
     volont
    0.42
    研究院
    0.40
     quotid
    0.40
     Castel
    0.39
     मामूली
    0.39
     quotidienne
    0.39
    ్ఞ
    0.38
    ROLL
    0.38
    Activations Density 0.003%

    No Known Activations