© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7123
    Prev
    Next
    INDEX
    Explanations

    be categorized or used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ÊN
    1.64
    φο
    1.62
     kunna
    1.58
    velope
    1.51
    くれる
    1.43
    ฬ
    1.42
    JZ
    1.38
    俎
    1.36
     relem
    1.35
    viene
    1.34
    POSITIVE LOGITS
     said
    1.68
     stressed
    1.52
     described
    1.51
     regretted
    1.51
    said
    1.48
    cited
    1.46
    去了
    1.45
     approximated
    1.44
    understood
    1.42
     likened
    1.40
    Activations Density 0.098%

    No Known Activations