© 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. 3430
    Prev
    Next
    INDEX
    Explanations

    network terms

    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
    zana
    1.54
    atenin
    1.48
    ăți
    1.46
    bica
    1.44
    怂
    1.42
     kaug
    1.41
    ardini
    1.40
    izadores
    1.40
    nader
    1.39
    ogne
    1.39
    POSITIVE LOGITS
    Ele
    1.26
    E
    1.19
    Ple
    1.19
     PLE
    1.18
     Ele
    1.15
    MPS
    1.15
    Dol
    1.10
     Pal
    1.10
    Pal
    1.08
     four
    1.07
    Activations Density 0.005%

    No Known Activations