© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10990
    Prev
    Next
    INDEX
    Explanations

    dive into, rice, soup, data handling, road

    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_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
     Mlad
    0.50
     Gruppe
    0.49
    ാരം
    0.46
    arzt
    0.41
    ឈ
    0.41
     gdyż
    0.41
    ഗു
    0.39
     avulla
    0.38
     അടിസ്ഥാന
    0.38
     आल्सो
    0.37
    POSITIVE LOGITS
    ilang
    0.42
     viewpoints
    0.39
    linetype
    0.38
     *_
    0.37
    Navigation
    0.36
     DET
    0.35
     있는데요
    0.35
    function
    0.35
     VCS
    0.35
    标准的
    0.34
    Activations Density 0.000%

    No Known Activations