© 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. 124868
    Prev
    Next
    INDEX
    Explanations

    through to, contact relationships, stretch

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

    Third unheard

    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
     אמ
    0.44
    ियर्स
    0.42
     аккумулятор
    0.42
     افت
    0.42
    //#
    0.41
    +'
    0.41
    ά
    0.41
    mx
    0.41
     सप्टेंबर
    0.41
    Académie
    0.41
    POSITIVE LOGITS
     Mahesh
    0.49
     Rahul
    0.46
    溶解
    0.46
     Nahin
    0.45
     Imran
    0.43
     directional
    0.43
     Suresh
    0.43
     restlessness
    0.42
     Bhuv
    0.42
     Rajesh
    0.42
    Activations Density 0.000%

    No Known Activations