© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 570
    Prev
    Next
    INDEX
    Explanations

    home appliances, person teaching, monetary domains

    np_acts-logits-general · gemini-2.5-flash-lite

    real-time information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    0.24
     phleg
    0.24
     jedoch
    0.23
     hér
    0.22
     fear
    0.21
     cependant
    0.21
     thei
    0.21
    }
    0.20
     thoe
    0.20
     asla
    0.20
    POSITIVE LOGITS
    一般来说
    0.20
     करणाऱ्या
    0.19
     வகையான
    0.19
    ционные
    0.19
     প্রক্রিয়া
    0.19
    蠵
    0.18
     जानिए
    0.18
     জনের
    0.18
    方的
    0.18
    以上的
    0.18
    Activations Density 0.637%

    No Known Activations