© 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. 28997
    Prev
    Next
    INDEX
    Explanations

    * properties

    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
    0.57
     is
    0.56
    i
    0.56
     in
    0.53
     scales
    0.51
    od
    0.50
    ρ
    0.49
     boards
    0.47
     was
    0.46
    ud
    0.46
    POSITIVE LOGITS
     行っ
    0.52
    ැ
    0.51
     Ró
    0.50
     أما
    0.49
     だけ
    0.48
    ):["
    0.48
     hambre
    0.48
     그러면은
    0.48
     haberse
    0.47
    ಿಗೆ
    0.47
    Activations Density 0.001%

    No Known Activations