© 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. 15-GEMMASCOPE-2-RES-262K
    7. 69891
    Prev
    Next
    INDEX
    Explanations

    gaze fixed, drifting, or lingering

    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_15_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
     glauben
    1.95
    het
    1.85
     creen
    1.72
     maken
    1.69
     bahagian
    1.66
    释
    1.65
    ettek
    1.64
     storie
    1.64
     bukti
    1.64
    槳
    1.62
    POSITIVE LOGITS
     Contacts
    1.18
     contacting
    1.15
     contacts
    1.09
     Contact
    1.06
    contacts
    1.06
     contact
    0.98
    Contact
    0.98
     invading
    0.97
     CONTACT
    0.95
    kontakt
    0.94
    Activations Density 0.005%

    No Known Activations