© 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. 105755
    Prev
    Next
    INDEX
    Explanations

    ticket, gas, no, the

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

    placeholder for

    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
     ಹ
    0.49
    SetValue
    0.47
    卻
    0.47
     我們
    0.46
    Tama
    0.46
     নাই
    0.46
    什麼
    0.46
    執
    0.46
    已經
    0.45
    就會
    0.45
    POSITIVE LOGITS
     invari
    0.46
    },
    0.44
     Sanitary
    0.41
     shorth
    0.41
     kombin
    0.41
     شیمی
    0.41
     propr
    0.40
     Paint
    0.40
     vilka
    0.39
     inspir
    0.39
    Activations Density 0.001%

    No Known Activations