© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6237
    Prev
    Next
    INDEX
    Explanations

    wear gloves or eye protection

    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
    Not in Any Lists

    No Comments

    Negative Logits
     VERY
    1.74
     很
    1.64
     REALLY
    1.62
    Unfortunately
    1.62
     ridiculously
    1.60
     horrible
    1.57
    以前
    1.57
    上面
    1.55
    問題
    1.53
     Unfortunately
    1.51
    POSITIVE LOGITS
    }})$
    1.47
    жек
    1.38
    accessories
    1.34
     acessórios
    1.34
    衍生
    1.29
    괄
    1.29
    ocaps
    1.28
    aggable
    1.27
    jelder
    1.27
     accesorios
    1.26
    Activations Density 0.299%

    No Known Activations