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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12949
    Prev
    Next
    INDEX
    Explanations

    basic features

    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
    i
    3.58
    <bos>
    3.13
    るのは
    2.98
    る
    2.73
    spec
    2.71
    スプレイ
    2.69
    𝙩
    2.64
    tanto
    2.64
    schaft
    2.63
    瘍
    2.60
    POSITIVE LOGITS
    요
    2.46
     y
    2.39
    ই
    2.33
    ఛ
    2.27
     minerals
    2.26
     Unle
    2.11
    াকৃত
    2.11
    曙
    2.11
     Bela
    2.10
    عد
    2.06
    Activations Density 0.023%

    No Known Activations