© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 635
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    爌
    1.94
    ^{*}=\
    1.91
    ＇
    1.90
     Cio
    1.86
    '}$
    1.86
     ベルト
    1.85
     بیچ
    1.84
    Õ
    1.83
    ilg
    1.83
    ']=
    1.82
    POSITIVE LOGITS
    0
    0.80
    7
    0.55
    5
    0.51
    6
    0.44
     clap
    0.43
     highland
    0.43
    8
    0.41
    4
    0.36
    毫米
    0.34
    uf
    0.33
    Activations Density 1.251%

    No Known Activations