© 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. 138286
    Prev
    Next
    INDEX
    Explanations

    Proposal discussions and details

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

    describing specific topics

    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
     സംഘ
    0.48
     shoots
    0.43
     इसमें
    0.42
     Lutheran
    0.41
    ¬
    0.41
    uclear
    0.40
    zyn
    0.39
     followed
    0.39
     militants
    0.39
    ù
    0.39
    POSITIVE LOGITS
    旸
    0.48
    梦想
    0.45
    짊
    0.45
     బంగారం
    0.44
    describe
    0.43
    来看看
    0.43
     поговорим
    0.43
     groene
    0.42
    鄒
    0.42
    迎接
    0.41
    Activations Density 0.005%

    No Known Activations