© 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. 16996
    Prev
    Next
    INDEX
    Explanations

    describes, validates, or specifies resource parameters

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

    EC2, VPC, RDS, AWS

    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
    พี่
    0.51
    猢
    0.50
     ጉዳ
    0.47
    ཕ
    0.45
    缑
    0.45
    ު
    0.44
    ི
    0.44
     বলিব
    0.44
    ཞ
    0.43
    ాల్
    0.43
    POSITIVE LOGITS
     specified
    0.58
     defined
    0.56
     identified
    0.56
     enabled
    0.56
     enables
    0.56
     identifies
    0.55
     information
    0.54
     requested
    0.53
     sampled
    0.52
     request
    0.52
    Activations Density 0.009%

    No Known Activations