© 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. 67129
    Prev
    Next
    INDEX
    Explanations

    water flows, dancers, lips, location, maximize

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

    correctly responding to instructions

    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
    frastructure
    0.46
    ॉट
    0.46
     साम्राज्य
    0.45
    ੋ
    0.44
    ুরু
    0.44
     installing
    0.44
     население
    0.43
     બાળકો
    0.43
    䜌
    0.43
     undermining
    0.43
    POSITIVE LOGITS
     ange
    0.48
     euh
    0.47
     agua
    0.46
     invern
    0.45
     estet
    0.44
     ビタミン
    0.44
     baños
    0.43
     appass
    0.43
     tych
    0.42
     ゴルフ
    0.42
    Activations Density 0.002%

    No Known Activations