Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 119785
    Prev
    Next
    INDEX
    Explanations

    zone boundaries

    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_40_width_262k_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
     químicos
    0.40
    inete
    0.40
     đức
    0.40
     répar
    0.40
     artificielle
    0.39
    <0x15>
    0.39
     espí
    0.39
     discrep
    0.38
     unsere
    0.38
     spaghetti
    0.37
    POSITIVE LOGITS
     συνα
    0.52
    eep
    0.39
     HIS
    0.37
     LoginForm
    0.37
     HIM
    0.37
     Notify
    0.37
    ऑ
    0.37
     σχ
    0.36
    Agen
    0.36
     normalize
    0.35
    Activations Density 0.001%

    No Known Activations