© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 550
    Prev
    Next
    INDEX
    Explanations

    Hierarchical BERT classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    unk
    0.98
    ental
    0.92
    kst
    0.91
    ointers
    0.90
     habido
    0.89
    inness
    0.88
    綬
    0.87
    onuclear
    0.86
    晤
    0.86
     &/
    0.86
    POSITIVE LOGITS
     Sc
    1.45
    Sc
    1.31
     Jasmine
    1.11
     scammers
    1.11
     Sim
    1.11
     complexity
    1.10
    简化
    1.10
     simulation
    1.09
    Sim
    1.08
     Miao
    1.08
    Activations Density 0.555%

    No Known Activations