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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1436
    Prev
    Next
    INDEX
    Explanations

    help followed by is, me, others, yourself, to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    களை
    1.73
    *{\
    1.61
    다고
    1.57
    க்
    1.55
    ונת
    1.53
    DOMstrings
    1.52
    cssMode
    1.50
    getStudentNo
    1.50
     useNavigate
    1.49
    ക്കൊ
    1.48
    POSITIVE LOGITS
    aal
    1.21
    osamente
    1.12
    大佬
    1.11
    forums
    1.10
    usik
    1.07
    呵呵
    1.04
     发表于
    1.02
    ↵
    1.00
    hall
    1.00
    ナル
    0.99
    Activations Density 0.012%

    No Known Activations