© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49960
    Prev
    Next
    INDEX
    Explanations

    measurement and instruction

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

    old, both, dreams, quick, varied, long

    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
    """
    0.44
    更多
    0.43
     additional
    0.42
    Y
    0.42
                
    0.42
     details
    0.41
       
    0.41
    :
    0.40
    K
    0.40
    ">
    0.40
    POSITIVE LOGITS
    ですし
    0.55
     आदमी
    0.50
    এবং
    0.50
     ludzi
    0.50
     અને
    0.49
     دائما
    0.49
     હંમે
    0.48
     거고
    0.48
    畛
    0.48
     लोकांना
    0.48
    Activations Density 0.001%

    No Known Activations