© 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. 44449
    Prev
    Next
    INDEX
    Explanations

    def area_or_volume(

    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
     proguardFiles
    0.46
    adapters
    0.40
    ставить
    0.40
     沙
    0.39
    hut
    0.38
    akuan
    0.38
     ).
    0.37
    চ্ছা
    0.37
    等到
    0.37
    ⁉
    0.37
    POSITIVE LOGITS
     its
    0.39
     inhabited
    0.38
     territorial
    0.37
    ສໍາ
    0.37
    <unused2125>
    0.36
    ิน
    0.36
     기본적인
    0.35
    لة
    0.35
     ਅਤੇ
    0.35
    ถนน
    0.35
    Activations Density 0.003%

    No Known Activations