© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 188440
    Prev
    Next
    INDEX
    Explanations

    three online, separate peace, digital pads

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

    body, trope, background, allow, support, curves

    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
    WIDE
    0.48
     Farmers
    0.47
     Daylight
    0.44
    रन
    0.44
    ı
    0.43
    atih
    0.42
    Farmers
    0.42
    ल्लाह
    0.42
    링
    0.42
    ন্টি
    0.42
    POSITIVE LOGITS
     infantil
    0.46
    oi
    0.42
     aur
    0.41
     aspecto
    0.41
     offenbar
    0.41
     neko
    0.40
    色素
    0.39
     nhi
    0.39
     مشابه
    0.39
     chup
    0.39
    Activations Density 0.001%

    No Known Activations