© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 304
    Prev
    Next
    INDEX
    Explanations

    verbs followed by objects

    np_acts-logits-general · gemini-2.5-flash-lite

    actions to explain or make

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     توسط
    0.46
     bằng
    0.45
     بواسطة
    0.44
     )
    0.41
     żeby
    0.40
     对于
    0.39
     путем
    0.39
     때문에
    0.37
    5
    0.37
     by
    0.37
    POSITIVE LOGITS
    גי
    0.44
    Cadastro
    0.40
    ון
    0.39
    Agu
    0.38
    Otros
    0.37
    Gambar
    0.37
    加え
    0.36
    Aid
    0.36
    ייט
    0.36
    Cantidad
    0.36
    Activations Density 0.699%

    No Known Activations