© 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. 4262
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

    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
    الم
    0.25
    Oste
    0.24
    الح
    0.24
    الط
    0.24
    ى
    0.23
    كل
    0.23
    تق
    0.23
    يط
    0.23
    ERRY
    0.22
    Heating
    0.22
    POSITIVE LOGITS
     JSON
    0.29
     metadata
    0.27
     UUID
    0.27
     mutex
    0.27
     메서
    0.26
     presenceData
    0.26
     java
    0.26
     filesystem
    0.26
     filenames
    0.25
     shards
    0.25
    Activations Density 0.000%

    No Known Activations