© 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. 249230
    Prev
    Next
    INDEX
    Explanations

    Adobe website optimization

    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
     incumb
    0.53
    ン
    0.53
    ט
    0.51
     emoticon
    0.49
     부
    0.49
     富
    0.48
     rumin
    0.47
    부
    0.46
    षेक
    0.46
     carreras
    0.45
    POSITIVE LOGITS
    ijk
    0.44
    \}$,
    0.43
     multitude
    0.42
     आईएफ
    0.42
    EEEE
    0.41
    balancing
    0.40
     dedicated
    0.40
     কৌ
    0.39
     விட்ட
    0.39
     المتع
    0.39
    Activations Density 0.003%

    No Known Activations