© 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-65K
    7. 20177
    Prev
    Next
    INDEX
    Explanations

    important section markers

    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_65k_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
    னோ
    0.49
     soğ
    0.46
    íd
    0.43
    rène
    0.42
    </h6>
    0.42
    嗇
    0.42
    ciò
    0.42
     Ella
    0.41
     Yum
    0.41
     ministro
    0.41
    POSITIVE LOGITS
    ة
    0.55
    י
    0.49
     TLR
    0.48
     సి
    0.48
     mea
    0.48
    ט
    0.47
    كه
    0.46
     общей
    0.46
     Т
    0.46
    اء
    0.45
    Activations Density 0.002%

    No Known Activations