© 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. 195654
    Prev
    Next
    INDEX
    Explanations

    building or selling

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

    actions safely

    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
    Ꮯ
    0.46
    Attenuation
    0.45
    ｔ
    0.44
     دیده
    0.44
    亳
    0.44
    拷
    0.43
    ТС
    0.42
    樋
    0.40
    ёг
    0.40
    quefois
    0.40
    POSITIVE LOGITS
     construcción
    0.56
     construit
    0.52
     penulis
    0.49
     scriv
    0.48
     constru
    0.47
     mendapatkan
    0.47
     déput
    0.47
     tarjeta
    0.46
     perusahaan
    0.46
    лко
    0.45
    Activations Density 0.001%

    No Known Activations