© 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. 53-GEMMASCOPE-2-RES-262K
    7. 34266
    Prev
    Next
    INDEX
    Explanations

    disconnects and detachments

    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_53_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
     அம்பேத்கர்
    0.47
    inelli
    0.39
    都道府県
    0.38
    埧
    0.38
     intArray
    0.37
    िष्ट
    0.37
    Teller
    0.36
    糟
    0.36
     Minority
    0.35
    Keb
    0.35
    POSITIVE LOGITS
     disconnect
    3.34
     disconnected
    3.23
     disconnection
    3.22
     disconnecting
    3.17
    disconnect
    2.95
    Disconnect
    2.94
    disconnected
    2.73
    Disconnected
    2.53
     detached
    2.27
     detachment
    2.17
    Activations Density 0.039%

    No Known Activations