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. 20455
    Prev
    Next
    INDEX
    Explanations

    latex commands

    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
    newcommand
    0.48
    )').
    0.39
     pade
    0.38
     Fonction
    0.37
     σ
    0.36
     highland
    0.36
     ανε
    0.36
    样例
    0.35
    щему
    0.35
     Roman
    0.35
    POSITIVE LOGITS
    $[\
    0.44
     Orphans
    0.42
     penalties
    0.42
     chasing
    0.41
     proteolytic
    0.41
    ᵖ
    0.41
     feme
    0.40
     abandoning
    0.40
     ulcers
    0.39
     thrombo
    0.39
    Activations Density 0.001%

    No Known Activations