© 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. 13753
    Prev
    Next
    INDEX
    Explanations

    starts with "la" or "without"

    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
     pre
    2.63
    ي
    2.60
    𝙡
    2.56
    ูก
    2.53
     gant
    2.53
     sp
    2.49
    и
    2.44
    ాన్ని
    2.43
    rgba
    2.39
    ッドレス
    2.37
    POSITIVE LOGITS
    ẩm
    2.69
    <bos>
    2.60
    संधान
    2.51
    য়া
    2.49
     לך
    2.46
    ੴ
    2.44
    蜍
    2.44
    ખ્ય
    2.38
    न्तर
    2.36
    शय
    2.27
    Activations Density 0.007%

    No Known Activations