© 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. 168109
    Prev
    Next
    INDEX
    Explanations

    actions followed by descriptions

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

    instruction, build, implement, facilitate, everything

    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
     conveying
    0.54
    NAB
    0.53
     Державний
    0.52
    اية
    0.51
    iyati
    0.51
    ander
    0.50
    𝟬
    0.49
    asına
    0.48
    ۰۰
    0.48
     असतो
    0.48
    POSITIVE LOGITS
    せ
    0.45
    Johnny
    0.43
    OVERRIDES
    0.43
     Lamp
    0.42
    上
    0.42
     didn
    0.42
     Geoff
    0.41
     দিন
    0.40
    界
    0.40
     sur
    0.39
    Activations Density 0.001%

    No Known Activations