© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 64239
    Prev
    Next
    INDEX
    Explanations

    break down, narrow down, nuanced details

    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
     Particularly
    0.45
    🙏🙏
    0.45
     Pemerintah
    0.44
     Zealand
    0.42
     Wellbeing
    0.41
     BlueprintName
    0.41
     Spawn
    0.41
     SafeArea
    0.41
     Housing
    0.40
    FeatureFlags
    0.40
    POSITIVE LOGITS
     telefone
    0.49
    industry
    0.45
    记
    0.45
     fabricantes
    0.45
    لیس
    0.44
    簡単に
    0.44
     élim
    0.44
     제대로
    0.44
     carbure
    0.43
    eliminate
    0.43
    Activations Density 0.049%

    No Known Activations