© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117337
    Prev
    Next
    INDEX
    Explanations

    when problems arise

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

    exploring news and events

    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_31_width_262k_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
    飲食店
    0.50
    ADOW
    0.44
    ન્દ
    0.43
     बत्रा
    0.43
     باقی
    0.43
    ્લા
    0.43
     এখানে
    0.42
    😺
    0.42
    ULATORY
    0.42
     장면
    0.41
    POSITIVE LOGITS
    ’.
    0.51
    យើង
    0.50
    uw
    0.49
    ’,
    0.49
    </strong>
    0.47
    et
    0.47
    uya
    0.47
    age
    0.46
    रण
    0.46
    णी
    0.46
    Activations Density 0.000%

    No Known Activations