© 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. 43959
    Prev
    Next
    INDEX
    Explanations

    thence and cardinal directions

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

    coordinates and vertices

    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
     bhavanti
    0.42
    ignano
    0.42
     abelian
    0.40
     univer
    0.39
    dziel
    0.39
    }]=
    0.39
     расстоя
    0.38
     abolished
    0.37
     infos
    0.37
    ACKS
    0.37
    POSITIVE LOGITS
     关闭
    0.46
     юго
    0.45
     τύ
    0.43
    दक्षिण
    0.42
     ফেরত
    0.41
    戻
    0.41
    🔙
    0.41
    を経て
    0.40
     topRight
    0.39
     retorn
    0.39
    Activations Density 0.005%

    No Known Activations