© 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. 117300
    Prev
    Next
    INDEX
    Explanations

    single axle trailer

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

    crucial first question or definition

    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
    BB
    0.50
    BM
    0.49
    apt
    0.45
    াদ
    0.44
    aked
    0.44
    emens
    0.44
    ټ
    0.44
    pH
    0.43
    Typed
    0.43
    aptops
    0.43
    POSITIVE LOGITS
     announce
    0.46
     outcast
    0.45
     Asc
    0.44
     arxiv
    0.44
    lás
    0.44
     equival
    0.43
     "+
    0.43
     caustic
    0.43
     VPC
    0.43
     Edge
    0.43
    Activations Density 0.000%

    No Known Activations