© 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. 131023
    Prev
    Next
    INDEX
    Explanations

    shoot down

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

    iconic sights

    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
    pathTo
    0.52
    𝐦
    0.48
    oust
    0.46
    gad
    0.46
    فق
    0.45
    örd
    0.45
    oed
    0.45
    ').':
    0.45
    கர
    0.44
    ිර
    0.43
    POSITIVE LOGITS
    別に
    0.50
    演唱
    0.46
     chieftain
    0.44
     dignissimos
    0.44
    運動
    0.43
    ိတ်
    0.43
    </h4>
    0.42
     iterated
    0.42
     एक्सरसाइज
    0.42
    Massage
    0.41
    Activations Density 0.000%

    No Known Activations