© 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. 13505
    Prev
    Next
    INDEX
    Explanations

    hyphenated or quoted phrases

    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
    圈
    2.40
    닌
    2.39
    지
    2.34
    র্থ
    2.31
    u
    2.31
    意思是
    2.28
     dugg
    2.19
    ive
    2.16
    잇
    2.16
    ization
    2.15
    POSITIVE LOGITS
    orithms
    3.05
    REETYPE
    2.97
    膩
    2.97
    ة
    2.97
    iflower
    2.73
    estep
    2.72
    ensed
    2.68
    rimazole
    2.59
    orithm
    2.57
     citric
    2.55
    Activations Density 0.000%

    No Known Activations