© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 773
    Prev
    Next
    INDEX
    Explanations

    numbers followed by plus or comma

    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_7_width_16k_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
    逅
    2.73
    ITH
    2.69
    𝐡
    2.63
    েন্দ
    2.61
    𝐰
    2.53
    氾
    2.50
    θαν
    2.47
    iyu
    2.45
     referrerpolicy
    2.40
    𝐢
    2.40
    POSITIVE LOGITS
    rd
    4.71
     rd
    2.97
    笘
    2.95
     तलाक
    2.95
    өрд
    2.86
     прав
    2.84
    quarters
    2.82
    rds
    2.77
    quarter
    2.68
    ﻂ
    2.66
    Activations Density 1.051%

    No Known Activations