© 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. 40813
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    describes how to solve

    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
    บ้าง
    0.48
    uillez
    0.40
    BorderSize
    0.39
    σία
    0.38
    MinIntensity
    0.37
    0.37
    TempVal
    0.37
    ⏳
    0.37
    やはり
    0.37
    urization
    0.36
    POSITIVE LOGITS
     khi
    0.44
     champions
    0.43
     BYU
    0.42
     爱
    0.42
     quando
    0.42
     hoera
    0.41
     unaffected
    0.41
     laaj
    0.41
     इन
    0.40
     workaround
    0.40
    Activations Density 0.000%

    No Known Activations