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. 31-GEMMASCOPE-2-RES-16K
    4. 11886
    Prev
    Next
    INDEX
    Explanations

    Related products or jobs

    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_16k_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
    性
    0.46
     max
    0.41
    riline
    0.41
     MAX
    0.39
    ]#
    0.38
    AYLOR
    0.38
    }`);
    0.38
    性的
    0.38
    リティ
    0.37
     समाप्ति
    0.37
    POSITIVE LOGITS
    Related
    0.41
     которые
    0.40
    autres
    0.40
     connexes
    0.39
     Herd
    0.39
     других
    0.38
    Comments
    0.38
     realizan
    0.38
     Related
    0.38
    ponsors
    0.37
    Activations Density 0.055%

    No Known Activations