© 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. 14647
    Prev
    Next
    INDEX
    Explanations

    running programs via ./

    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
    𝐬
    2.79
    𝐞
    2.56
    𝐠
    2.43
    𝐥
    2.39
    __(/*!
    2.38
    ᠠ
    2.33
     NSA
    2.32
     PRS
    2.32
    𝐭
    2.31
     Access
    2.28
    POSITIVE LOGITS
    ಿ
    2.64
    ין
    2.52
    ంజ
    2.42
    꼭
    2.35
    sé
    2.34
    賂
    2.33
    s
    2.32
    ු
    2.28
    oğlu
    2.25
    iť
    2.24
    Activations Density 0.014%

    No Known Activations