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. 53-GEMMASCOPE-2-RES-262K
    4. 14172
    Prev
    Next
    INDEX
    Explanations

    legal court cases and documents

    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_53_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
     teorie
    0.44
     Elektrokh
    0.44
    Gosudarstvennyj
    0.44
    తోంది
    0.43
    unsaturated
    0.43
     teoría
    0.43
    畕
    0.42
    theory
    0.41
     राजप
    0.41
     கோட்ப
    0.41
    POSITIVE LOGITS
     tort
    0.46
     "[
    0.42
     distress
    0.42
     Plaintiff
    0.39
     accord
    0.39
    <sup>
    0.39
     dig
    0.38
    Tort
    0.38
    /**
    0.38
     “[
    0.38
    Activations Density 0.002%

    No Known Activations