© 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. 231556
    Prev
    Next
    INDEX
    Explanations

    Software and adventures

    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
    чен
    0.57
    ському
    0.55
    ських
    0.53
    ματος
    0.51
    шення
    0.51
    смотрим
    0.50
    𝗽
    0.49
    இதில்
    0.49
    𝗮
    0.48
    ця
    0.48
    POSITIVE LOGITS
     Software
    0.58
     $
    0.54
    Software
    0.54
     software
    0.52
    软件
    0.47
     hå
    0.46
     meta
    0.45
     adventure
    0.44
     endurance
    0.44
     Adventures
    0.44
    Activations Density 0.000%

    No Known Activations