© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 27644
    Prev
    Next
    INDEX
    Explanations

    purpose, cleaning, rise, rackets, ellipse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    成
    0.43
     মানিক
    0.42
    وص
    0.39
    حد
    0.38
     bowiem
    0.38
     thành
    0.37
     drawable
    0.37
     Вики
    0.37
     débat
    0.37
    迄
    0.37
    POSITIVE LOGITS
    igh
    0.39
    ased
    0.37
     dark
    0.36
     எஸ்
    0.36
    Retro
    0.36
     artich
    0.36
     એલ
    0.36
    tais
    0.36
    ito
    0.35
     तय
    0.34
    Activations Density 0.001%

    No Known Activations