© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8041
    Prev
    Next
    INDEX
    Explanations

    m followed by period

    np_acts-logits-general · gemini-2.5-flash-lite

    code object attribute access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >),
    0.43
    ())
    0.36
    .=
    0.35
    is
    0.34
    _='
    0.34
    ₁)
    0.34
    =${
    0.34
    _
    0.33
    "/>
    0.33
    ramos
    0.33
    POSITIVE LOGITS
    педії
    0.40
    CriteriaUtils
    0.40
     ブレスレット
    0.35
     speedboat
    0.35
    ActivityCompat
    0.34
     আনুষ্ঠান
    0.33
     princípio
    0.33
    G
    0.33
    ૢ
    0.33
     Aquaculture
    0.32
    Activations Density 0.000%

    No Known Activations