© 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. 5013
    Prev
    Next
    INDEX
    Explanations

    longboarding, singular, heat, CAD, distribution, corkscrew, community, Twitter

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

    performance marketing

    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
    <unused60>
    0.39
    entgen
    0.36
    <td>
    0.35
     lym
    0.35
    </b>
    0.35
    </code>
    0.35
    <0xEC>
    0.34
     Http
    0.33
     \
    0.33
     http
    0.33
    POSITIVE LOGITS
    ogenesis
    0.36
    جات
    0.35
    ತೆಗೆ
    0.35
    ків
    0.34
    ጆች
    0.34
    林的
    0.32
    വും
    0.32
    りを
    0.31
     virkelig
    0.31
    মির
    0.31
    Activations Density 0.278%

    No Known Activations