© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3915
    Prev
    Next
    INDEX
    Explanations

    labeling or identifying labels

    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_12_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
    ucky
    1.29
    ophane
    1.28
     hotspot
    1.21
     shelter
    1.18
     Kuk
    1.18
    ishman
    1.16
    utica
    1.15
     #-
    1.12
     Stranger
    1.11
    ther
    1.11
    POSITIVE LOGITS
    ́c
    1.51
    ensus
    1.45
    comodule
    1.39
    ábbi
    1.37
    ECM
    1.35
    ács
    1.32
    çoit
    1.32
     Lightroom
    1.32
    总经理
    1.31
     département
    1.31
    Activations Density 0.000%

    No Known Activations