© 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. 219805
    Prev
    Next
    INDEX
    Explanations

    use information or price

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

    princess and workplaces

    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
     vải
    0.48
     downtown
    0.47
     públic
    0.46
     rumble
    0.43
     sofá
    0.42
    博
    0.41
    电视
    0.41
    ర్కొ
    0.41
    پا
    0.40
    ান্তি
    0.40
    POSITIVE LOGITS
     করিয়াছি
    0.46
    bindingFields
    0.43
    ukh
    0.40
    iding
    0.40
    does
    0.40
    ){\
    0.39
    nce
    0.39
    URUK
    0.39
    𝑘
    0.39
     नियुक्ति
    0.39
    Activations Density 0.000%

    No Known Activations